Upload folder using huggingface_hub

LICENSE.txt

@@ -0,0 +1,111 @@
+LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
+Llama 3.2 Version Release Date: September 25, 2024
+
+“Agreement” means the terms and conditions for use, reproduction, distribution 
+and modification of the Llama Materials set forth herein.
+
+“Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
+distributed by Meta at https://llama.meta.com/doc/overview.
+
+“Licensee” or “you” means you, or your employer or any other person or entity (if you are 
+entering into this Agreement on such person or entity’s behalf), of the age required under
+applicable laws, rules or regulations to provide legal consent and that has legal authority
+to bind your employer or such other person or entity if you are entering in this Agreement
+on their behalf.
+
+“Llama 3.2” means the foundational large language models and software and algorithms, including
+machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
+fine-tuning enabling code and other elements of the foregoing distributed by Meta at 
+https://www.llama.com/llama-downloads.
+
+“Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and 
+any portion thereof) made available under this Agreement.
+
+“Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, 
+if you are an entity, your principal place of business is in the EEA or Switzerland) 
+and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+
+By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
+you agree to be bound by this Agreement.
+
+
+1. License Rights and Redistribution.
+
+    a. Grant of Rights. You are granted a non-exclusive, worldwide, 
+non-transferable and royalty-free limited license under Meta’s intellectual property or other rights 
+owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works 
+of, and make modifications to the Llama Materials.  
+
+    b. Redistribution and Use.  
+
+        i. If you distribute or make available the Llama Materials (or any derivative works thereof), 
+or a product or service (including another AI model) that contains any of them, you shall (A) provide
+a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
+on a related website, user interface, blogpost, about page, or product documentation. If you use the
+Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
+otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
+at the beginning of any such AI model name.
+
+        ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
+of an integrated end user product, then Section 2 of this Agreement will not apply to you. 
+
+        iii. You must retain in all copies of the Llama Materials that you distribute the 
+following attribution notice within a “Notice” text file distributed as a part of such copies: 
+“Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
+Inc. All Rights Reserved.”
+
+        iv. Your use of the Llama Materials must comply with applicable laws and regulations
+(including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
+the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby 
+incorporated by reference into this Agreement.
+  
+2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
+of the products or services made available by or for Licensee, or Licensee’s affiliates, 
+is greater than 700 million monthly active users in the preceding calendar month, you must request 
+a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
+exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+
+3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND 
+RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
+ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
+OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
+FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
+WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+
+4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, 
+WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, 
+FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+
+5. Intellectual Property.
+
+    a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, 
+neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, 
+except as required for reasonable and customary use in describing and redistributing the Llama Materials or as 
+set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required 
+to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible 
+at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark 
+will inure to the benefit of Meta.
+
+    b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
+    derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
+    you are and will be the owner of such derivative works and modifications.
+
+    c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
+    counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
+    of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
+    by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
+    claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
+    party arising out of or related to your use or distribution of the Llama Materials.
+
+6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
+to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
+and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
+Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
+4 and 7 shall survive the termination of this Agreement. 
+
+7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of 
+California without regard to choice of law principles, and the UN Convention on Contracts for the International
+Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
+any dispute arising out of this Agreement. 

README.md

@@ -0,0 +1,495 @@
+---
+language:
+- en
+- de
+- fr
+- it
+- pt
+- hi
+- es
+- th
+library_name: transformers
+pipeline_tag: image-text-to-text
+tags:
+- facebook
+- meta
+- pytorch
+- llama
+- llama-3
+widget:
+  - example_title: rococo art
+    messages:
+      - role: user
+        content:
+          - type: text
+            text: Which era does this piece belong to? Give details about the era.
+          - type: image_url
+            image_url:
+              url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/rococo.jpg
+      - role: assistant
+        content: |
+          The piece is a painting of a woman in a red dress, surrounded by gold and white ornate details. The woman is depicted in mid-air, with her arms outstretched and her legs bent at the knees. She is holding a bouquet of flowers in her right hand and a fruit in her left hand.
+          
+          The background of the painting is a light blue sky with pink clouds, and there are also some pink flowers and green leaves surrounding the woman. The overall atmosphere of the painting is one of joy and celebration, as if the woman is dancing or celebrating something.
+          
+          This piece belongs to the Rococo era, which was a style of art and architecture that emerged in Europe in the 18th century. The Rococo style is characterized by its use of pastel colors, curved lines, and ornate details. It was popularized during the reign of King Louis XV of France, who ruled from 1715 to 1774.
+  - example_title: diagram understanding
+    messages:
+      - role: user
+        content:
+          - type: text
+            text: Where do the droughts happen according to this diagram?
+          - type: image_url
+            image_url:
+              url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/weather_events.png
+      - role: assistant
+        content: |
+          # Drought Regions in 2016
+          
+          According to the diagram, the regions that experienced severe droughts in 2016 are:
+          
+          - **Eastern and Southern Africa**: This region was severely affected by droughts, with significant impacts on agriculture and water resources.
+          - **Western and Southern Africa**: Droughts also occurred in this region, leading to food insecurity and other challenges.
+          
+          These regions were particularly vulnerable to droughts in 2016, highlighting the need for effective water management strategies and climate resilience measures.
+  - example_title: document qa
+    messages:
+      - role: user
+        content:
+          - type: text
+            text: How long does it take from invoice date to due date? Be short and concise.
+          - type: image_url
+            image_url:
+              url: https://huggingface.co/datasets/huggingface/release-assets/resolve/main/invoice.png
+      - role: assistant
+        content: |
+          To determine the time gap between the invoice date and the due date, we need to calculate the difference between these two dates.
+          
+          Invoice Date: February 11, 2019
+          Due Date: February 26, 2019
+          
+          Step 1: Calculate the Difference in Days
+          
+          February 26 - February 11 = 15 days
+          
+          Therefore, the time gap between the invoice date and the due date is 15 days.
+license: llama3.2
+extra_gated_prompt: >-
+  ### LLAMA 3.2 COMMUNITY LICENSE AGREEMENT
+
+
+  Llama 3.2 Version Release Date: September 25, 2024
+
+  
+  “Agreement” means the terms and conditions for use, reproduction, distribution 
+  and modification of the Llama Materials set forth herein.
+
+  
+  “Documentation” means the specifications, manuals and documentation accompanying Llama 3.2
+  distributed by Meta at https://llama.meta.com/doc/overview.
+
+  
+  “Licensee” or “you” means you, or your employer or any other person or entity (if you are 
+  entering into this Agreement on such person or entity’s behalf), of the age required under
+  applicable laws, rules or regulations to provide legal consent and that has legal authority
+  to bind your employer or such other person or entity if you are entering in this Agreement
+  on their behalf.
+
+  
+  “Llama 3.2” means the foundational large language models and software and algorithms, including
+  machine-learning model code, trained model weights, inference-enabling code, training-enabling code,
+  fine-tuning enabling code and other elements of the foregoing distributed by Meta at 
+  https://www.llama.com/llama-downloads.
+
+  
+  “Llama Materials” means, collectively, Meta’s proprietary Llama 3.2 and Documentation (and 
+  any portion thereof) made available under this Agreement.
+
+  
+  “Meta” or “we” means Meta Platforms Ireland Limited (if you are located in or, 
+  if you are an entity, your principal place of business is in the EEA or Switzerland) 
+  and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland). 
+
+
+  By clicking “I Accept” below or by using or distributing any portion or element of the Llama Materials,
+  you agree to be bound by this Agreement.
+
+  
+  1. License Rights and Redistribution.
+  
+  a. Grant of Rights. You are granted a non-exclusive, worldwide, 
+  non-transferable and royalty-free limited license under Meta’s intellectual property or other rights 
+  owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works 
+  of, and make modifications to the Llama Materials.  
+
+  b. Redistribution and Use.  
+
+  i. If you distribute or make available the Llama Materials (or any derivative works thereof), 
+  or a product or service (including another AI model) that contains any of them, you shall (A) provide
+  a copy of this Agreement with any such Llama Materials; and (B) prominently display “Built with Llama”
+  on a related website, user interface, blogpost, about page, or product documentation. If you use the
+  Llama Materials or any outputs or results of the Llama Materials to create, train, fine tune, or
+  otherwise improve an AI model, which is distributed or made available, you shall also include “Llama”
+  at the beginning of any such AI model name.
+
+  ii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part
+  of an integrated end user product, then Section 2 of this Agreement will not apply to you. 
+
+  iii. You must retain in all copies of the Llama Materials that you distribute the 
+  following attribution notice within a “Notice” text file distributed as a part of such copies: 
+  “Llama 3.2 is licensed under the Llama 3.2 Community License, Copyright © Meta Platforms,
+  Inc. All Rights Reserved.”
+
+  iv. Your use of the Llama Materials must comply with applicable laws and regulations
+  (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for
+  the Llama Materials (available at https://www.llama.com/llama3_2/use-policy), which is hereby 
+  incorporated by reference into this Agreement.
+    
+  2. Additional Commercial Terms. If, on the Llama 3.2 version release date, the monthly active users
+  of the products or services made available by or for Licensee, or Licensee’s affiliates, 
+  is greater than 700 million monthly active users in the preceding calendar month, you must request 
+  a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to
+  exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.
+  
+  3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND 
+  RESULTS THEREFROM ARE PROVIDED ON AN “AS IS” BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS
+  ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES
+  OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE
+  FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED
+  WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.
+  
+  4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, 
+  WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, 
+  FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN 
+  IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.
+  
+  5. Intellectual Property.
+  
+  a. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, 
+  neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, 
+  except as required for reasonable and customary use in describing and redistributing the Llama Materials or as 
+  set forth in this Section 5(a). Meta hereby grants you a license to use “Llama” (the “Mark”) solely as required 
+  to comply with the last sentence of Section 1.b.i. You will comply with Meta’s brand guidelines (currently accessible 
+  at https://about.meta.com/brand/resources/meta/company-brand/). All goodwill arising out of your use of the Mark 
+  will inure to the benefit of Meta.
+  
+  b. Subject to Meta’s ownership of Llama Materials and derivatives made by or for Meta, with respect to any
+  derivative works and modifications of the Llama Materials that are made by you, as between you and Meta,
+  you are and will be the owner of such derivative works and modifications.
+
+  c. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or
+  counterclaim in a lawsuit) alleging that the Llama Materials or Llama 3.2 outputs or results, or any portion
+  of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable
+  by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or
+  claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third
+  party arising out of or related to your use or distribution of the Llama Materials.
+  
+  6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access
+  to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms
+  and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this
+  Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3,
+  4 and 7 shall survive the termination of this Agreement. 
+  
+  7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of 
+  California without regard to choice of law principles, and the UN Convention on Contracts for the International
+  Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of
+  any dispute arising out of this Agreement. 
+  
+  ### Llama 3.2 Acceptable Use Policy
+  
+  Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. 
+  If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). 
+  The most recent copy of this policy can be found at
+  [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
+  
+  #### Prohibited Uses
+  
+  We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
+  
+  1. Violate the law or others’ rights, including to:
+      1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
+          1. Violence or terrorism
+          2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+          3. Human trafficking, exploitation, and sexual violence
+          4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+          5. Sexual solicitation
+          6. Any other criminal activity
+      1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+      2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+      3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
+      4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
+      5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
+      6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
+      7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
+  2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
+      8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
+      9. Guns and illegal weapons (including weapon development)
+      10. Illegal drugs and regulated/controlled substances
+      11. Operation of critical infrastructure, transportation technologies, or heavy machinery
+      12. Self-harm or harm to others, including suicide, cutting, and eating disorders
+      13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+  3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
+      14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+      15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+      16. Generating, promoting, or further distributing spam
+      17. Impersonating another individual without consent, authorization, or legal right
+      18. Representing that the use of Llama 3.2 or outputs are human-generated
+      19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+  4. Fail to appropriately disclose to end users any known dangers of your AI system
+  5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
+
+
+  With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
+
+
+  Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+
+  * Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
+  
+  * Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+  
+  * Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+  
+  * Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com
+extra_gated_fields:
+  First Name: text
+  Last Name: text
+  Date of birth: date_picker
+  Country: country
+  Affiliation: text
+  Job title:
+    type: select
+    options:
+    - Student
+    - Research Graduate
+    - AI researcher
+    - AI developer/engineer
+    - Reporter
+    - Other
+  geo: ip_location
+  By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy: checkbox
+extra_gated_description: >-
+  The information you provide will be collected, stored, processed and shared in
+  accordance with the [Meta Privacy
+  Policy](https://www.facebook.com/privacy/policy/).
+extra_gated_button_content: Submit
+extra_gated_eu_disallowed: true
+---
+
+## Model Information
+
+The Llama 3.2-Vision collection of multimodal large language models (LLMs) is a collection of pretrained and instruction-tuned image reasoning generative models in 11B and 90B sizes (text \+ images in / text out). The Llama 3.2-Vision instruction-tuned models are optimized for visual recognition, image reasoning, captioning, and answering general questions about an image. The models outperform many of the available open source and closed multimodal models on common industry benchmarks.
+
+**Model Developer**: Meta
+
+**Model Architecture:** Llama 3.2-Vision is built on top of Llama 3.1 text-only model, which is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. To support image recognition tasks, the Llama 3.2-Vision model uses a separately trained vision adapter that integrates with the pre-trained Llama 3.1 language model. The adapter consists of a series of cross-attention layers that feed image encoder representations into the core LLM.
+
+|  | Training Data | Params | Input modalities | Output modalities | Context length | GQA | Data volume | Knowledge cutoff |
+| :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- | :---- |
+| Llama 3.2-Vision  | (Image, text) pairs | 11B (10.6) | Text \+ Image | Text  | 128k | Yes | 6B (image, text) pairs | December 2023 |
+| Llama 3.2-Vision | (Image, text) pairs | 90B (88.8) | Text \+ Image | Text  | 128k | Yes | 6B (image, text) pairs  | December 2023 |
+
+**Supported Languages:** For text only tasks, English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai are officially supported. Llama 3.2 has been trained on a broader collection of languages than these 8 supported languages. Note for image+text applications, English is the only language supported. 
+
+Developers may fine-tune Llama 3.2 models for languages beyond these supported languages, provided they comply with the Llama 3.2 Community License and the Acceptable Use Policy. Developers are always expected to ensure that their deployments, including those that involve additional languages, are completed safely and responsibly.
+
+**Llama 3.2 Model Family:** Token counts refer to pretraining data only. All model versions use Grouped-Query Attention (GQA) for improved inference scalability.
+
+**Model Release Date:** Sept 25, 2024
+
+**Status:** This is a static model trained on an offline dataset. Future versions may be released that improve model capabilities and safety. 
+
+**License:** Use of Llama 3.2 is governed by the [Llama 3.2 Community License](https://github.com/meta-llama/llama-models/blob/main/models/llama3_2/LICENSE) (a custom, commercial license agreement).
+
+**Feedback:** Where to send questions or comments about the model Instructions on how to provide feedback or comments on the model can be found in the model [README](https://github.com/meta-llama/llama-models/tree/main/models/llama3_2). For more technical information about generation parameters and recipes for how to use Llama 3.2-Vision in applications, please go [here](https://github.com/meta-llama/llama-recipes). 
+
+## Intended Use
+
+**Intended Use Cases:** Llama 3.2-Vision is intended for commercial and research use. Instruction tuned models are intended for visual recognition, image reasoning, captioning, and assistant-like chat with images, whereas pretrained models can be adapted for a variety of image reasoning tasks. Additionally, because of Llama 3.2-Vision’s ability to take images and text as inputs, additional use cases could include:
+
+1. Visual Question Answering (VQA) and Visual Reasoning: Imagine a machine that looks at a picture and understands your questions about it.   
+2. Document Visual Question Answering (DocVQA): Imagine a computer understanding both the text and layout of a document, like a map or contract, and then answering questions about it directly from the image.  
+3. Image Captioning: Image captioning bridges the gap between vision and language, extracting details, understanding the scene, and then crafting a sentence or two that tells the story.  
+4. Image-Text Retrieval: Image-text retrieval is like a matchmaker for images and their descriptions. Similar to a search engine but one that understands both pictures and words.  
+5. Visual Grounding: Visual grounding is like connecting the dots between what we see and say. It’s about understanding how language references specific parts of an image, allowing AI models to pinpoint objects or regions based on natural language descriptions.  
+   
+
+The Llama 3.2 model collection also supports the ability to leverage the outputs of its models to improve other models including synthetic data generation and distillation. The Llama 3.2 Community License allows for these use cases. 
+
+**Out of Scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in any other way that is prohibited by the Acceptable Use Policy and Llama 3.2 Community License. Use in languages beyond those explicitly referenced as supported in this model card.
+
+## How to use
+
+This repository contains two versions of Llama-3.2-11B-Vision-Instruct, for use with transformers and with the original `llama` codebase.
+
+### Use with transformers
+
+Starting with transformers >= 4.45.0 onward, you can run inference using conversational messages that may include an image you can query about.
+
+Make sure to update your transformers installation via `pip install --upgrade transformers`.
+
+```python
+import requests
+import torch
+from PIL import Image
+from transformers import MllamaForConditionalGeneration, AutoProcessor
+
+model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
+
+model = MllamaForConditionalGeneration.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+)
+processor = AutoProcessor.from_pretrained(model_id)
+
+url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/0052a70beed5bf71b92610a43a52df6d286cd5f3/diffusers/rabbit.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+messages = [
+    {"role": "user", "content": [
+        {"type": "image"},
+        {"type": "text", "text": "If I had to write a haiku for this one, it would be: "}
+    ]}
+]
+input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
+inputs = processor(
+    image,
+    input_text,
+    add_special_tokens=False,
+    return_tensors="pt"
+).to(model.device)
+
+output = model.generate(**inputs, max_new_tokens=30)
+print(processor.decode(output[0]))
+```
+
+### Use with `llama`
+
+Please, follow the instructions in the [repository](https://github.com/meta-llama/llama).
+
+To download the original checkpoints, you can use `huggingface-cli` as follows:
+
+```
+huggingface-cli download meta-llama/Llama-3.2-11B-Vision-Instruct --include "original/*" --local-dir Llama-3.2-11B-Vision-Instruct
+```
+
+## Hardware and Software
+
+**Training Factors:** We used custom training libraries, Meta's custom built GPU cluster, and production infrastructure for pretraining. Fine-tuning, annotation, and evaluation were also performed on production infrastructure.
+
+**Training Energy Use:** Training utilized a cumulative of **2.02M** GPU hours of computation on H100-80GB (TDP of 700W) type hardware, per the table below. Training time is the total GPU time required for training each model and power consumption is the peak power capacity per GPU device used, adjusted for power usage efficiency. 
+
+## 
+
+**Training Greenhouse Gas Emissions:** Estimated total location-based greenhouse gas emissions were **584** tons CO2eq for training. Since 2020, Meta has maintained net zero greenhouse gas emissions in its global operations and matched 100% of its electricity use with renewable energy, therefore the total market-based greenhouse gas emissions for training were 0 tons CO2eq.
+
+|  | Training Time (GPU hours) | Training Power Consumption (W) | Training Location-Based Greenhouse Gas Emissions (tons CO2eq) | Training Market-Based Greenhouse Gas Emissions (tons CO2eq) |
+| :---- | :---: | :---: | :---: | :---: |
+| Llama 3.2-vision 11B | Stage 1 pretraining: 147K H100 hours Stage 2 annealing: 98K H100 hours SFT: 896 H100 hours RLHF: 224 H100 hours | 700 | 71 | 0 |
+| Llama 3.2-vision 90B | Stage 1 pretraining: 885K H100 hours Stage 2 annealing: 885K H100 hours SFT: 3072 H100 hours RLHF: 2048 H100 hours | 700 | 513 | 0 |
+| Total | 2.02M |  | 584 | 0 |
+
+The methodology used to determine training energy use and greenhouse gas emissions can be found [here](https://arxiv.org/pdf/2204.05149).  Since Meta is openly releasing these models, the training energy use and greenhouse gas emissions will not be incurred by others.
+
+## Training Data
+
+**Overview:** Llama 3.2-Vision was pretrained on 6B image and text pairs. The instruction tuning data includes publicly available vision instruction datasets, as well as over 3M synthetically generated examples.
+
+**Data Freshness:** The pretraining data has a cutoff of December 2023\.
+
+## Benchmarks \- Image Reasoning
+
+In this section, we report the results for Llama 3.2-Vision models on standard automatic benchmarks. For all these evaluations, we used our internal evaluations library.
+
+### Base Pretrained Models
+
+| Category | Benchmark | \# Shots | Metric | Llama 3.2 11B | Llama 3.2 90B |
+| ----- | ----- | ----- | ----- | ----- | ----- |
+| Image Understanding | VQAv2 (val) | 0 | Accuracy | 66.8 | 73.6 |
+|  | Text VQA (val) | 0 | Relaxed accuracy | 73.1 | 73.5 |
+|  | DocVQA (val, unseen) | 0 | ANLS | 62.3 | 70.7 |
+| Visual Reasoning | MMMU (val, 0-shot) | 0 | Micro average accuracy | 41.7 | 49.3 |
+|  | ChartQA (test) | 0 | Accuracy | 39.4 | 54.2 |
+|  | InfographicsQA (val, unseen) | 0 | ANLS | 43.2 | 56.8 |
+|  | AI2 Diagram (test) | 0 | Accuracy | 62.4 | 75.3 |
+
+### Instruction Tuned Models
+
+| Modality | Capability | Benchmark | \# Shots | Metric | Llama 3.2 11B | Llama 3.2 90B |
+| ----- | :---: | ----- | :---: | :---: | ----- | ----- |
+| Image | College-level Problems and Mathematical Reasoning | MMMU (val, CoT) | 0 | Micro average accuracy | 50.7 | 60.3 |
+|  |  | MMMU-Pro, Standard (10 opts, test) | 0 | Accuracy | 33.0 | 45.2 |
+|  |  | MMMU-Pro, Vision (test) | 0 | Accuracy | 23.7 | 33.8 |
+|  |  | MathVista (testmini) | 0 | Accuracy | 51.5 | 57.3 |
+|  | Charts and Diagram Understanding | ChartQA (test, CoT) | 0 | Relaxed accuracy | 83.4 | 85.5 |
+|  |  | AI2 Diagram (test) | 0 | Accuracy | 91.1 | 92.3 |
+|  |  | DocVQA (test) | 0 | ANLS | 88.4 | 90.1 |
+|  | General Visual Question Answering | VQAv2 (test) | 0 | Accuracy | 75.2 | 78.1 |
+|  |  |  |  |  |  |  |
+| Text | General | MMLU (CoT) | 0 | Macro\_avg/acc | 73.0 | 86.0 |
+|  | Math | MATH (CoT) | 0 | Final\_em | 51.9 | 68.0 |
+|  | Reasoning | GPQA | 0 | Accuracy | 32.8 | 46.7 |
+|  | Multilingual | MGSM (CoT) | 0 | em | 68.9 | 86.9 |
+
+## Responsibility & Safety
+
+As part of our Responsible release approach, we followed a three-pronged strategy to managing trust & safety risks:
+
+1. Enable developers to deploy helpful, safe and flexible experiences for their target audience and for the use cases supported by Llama.   
+2. Protect developers against adversarial users aiming to exploit Llama capabilities to potentially cause harm.  
+3. Provide protections for the community to help prevent the misuse of our models.
+
+### Responsible Deployment 
+
+**Approach:** Llama is a foundational technology designed to be used in a variety of use cases, examples on how Meta’s Llama models have been responsibly deployed can be found in our [Community Stories webpage](https://llama.meta.com/community-stories/). Our approach is to build the most helpful models enabling the world to benefit from the technology power, by aligning our model safety for the generic use cases addressing a standard set of harms. Developers are then in the driver seat to tailor safety for their use case, defining their own policy and deploying the models with the necessary safeguards in their Llama systems. Llama 3.2 was developed following the best practices outlined in our Responsible Use Guide, you can refer to the [Responsible Use Guide](https://llama.meta.com/responsible-use-guide/) to learn more. 
+
+#### Llama 3.2 Instruct 
+
+**Objective:** Our main objectives for conducting safety fine-tuning are to provide the research community with a valuable resource for studying the robustness of safety fine-tuning, as well as to offer developers a readily available, safe, and powerful model for various applications to reduce the developer workload to deploy safe AI systems. We implemented the same set of safety mitigations as in Llama 3, and you can learn more about these in the Llama 3 [paper](https://ai.meta.com/research/publications/the-llama-3-herd-of-models/).
+
+**Fine-Tuning Data:** We employ a multi-faceted approach to data collection, combining human-generated data from our vendors with synthetic data to mitigate potential safety risks. We’ve developed many large language model (LLM)-based classifiers that enable us to thoughtfully select high-quality prompts and responses, enhancing data quality control. 
+
+**Refusals and Tone:** Building on the work we started with Llama 3, we put a great emphasis on model refusals to benign prompts as well as refusal tone. We included both borderline and adversarial prompts in our safety data strategy, and modified our safety data responses to follow tone guidelines.
+
+#### Llama 3.2 Systems
+
+**Safety as a System:** Large language models, including Llama 3.2, **are not designed to be deployed in isolation** but instead should be deployed as part of an overall AI system with additional safety guardrails as required. Developers are expected to deploy system safeguards when building agentic systems. Safeguards are key to achieve the right helpfulness-safety alignment as well as mitigating safety and security risks inherent to the system and any integration of the model or system with external tools. As part of our responsible release approach, we provide the community with [safeguards](https://llama.meta.com/trust-and-safety/) that developers should deploy with Llama models or other LLMs, including Llama Guard, Prompt Guard and Code Shield. All our [reference implementations](https://github.com/meta-llama/llama-agentic-system) demos contain these safeguards by default so developers can benefit from system-level safety out-of-the-box. 
+
+### New Capabilities and Use Cases
+
+**Technological Advancement:** Llama releases usually introduce new capabilities that require specific considerations in addition to the best practices that generally apply across all Generative AI use cases. For prior release capabilities also supported by Llama 3.2, see [Llama 3.1 Model Card](https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md), as the same considerations apply here as well., 
+
+**Image Reasoning:** Llama 3.2-Vision models come with multimodal (text and image) input capabilities enabling image reasoning applications. As part of our responsible release process, we took dedicated measures including evaluations and mitigations to address the risk of the models uniquely identifying individuals in images. As with other LLM risks, models may not always be robust to adversarial prompts, and developers should evaluate identification and other applicable risks in the context of their applications as well as consider deploying Llama Guard 3-11B-Vision as part of their system or other mitigations as appropriate to detect and mitigate such risks.
+
+### Evaluations
+
+**Scaled Evaluations:** We built dedicated, adversarial evaluation datasets and evaluated systems composed of Llama models and Purple Llama safeguards to filter input prompt and output response. It is important to evaluate applications in context, and we recommend building dedicated evaluation dataset for your use case. 
+
+**Red teaming:** We conducted recurring red teaming exercises with the goal of discovering risks via adversarial prompting and we used the learnings to improve our benchmarks and safety tuning datasets. We partnered early with subject-matter experts in critical risk areas to understand the nature of these real-world harms and how such models may lead to unintended harm for society. Based on these conversations, we derived a set of adversarial goals for the red team to attempt to achieve, such as extracting harmful information or reprogramming the model to act in a potentially harmful capacity. The red team consisted of experts in cybersecurity, adversarial machine learning, responsible AI, and integrity in addition to multilingual content specialists with background in integrity issues in specific geographic markets.
+
+### Critical Risks 
+
+In addition to our safety work above, we took extra care on measuring and/or mitigating the following critical risk areas:
+
+**1\. CBRNE (Chemical, Biological, Radiological, Nuclear, and Explosive Weapons):** For Llama 3.1, to assess risks related to proliferation of chemical and biological weapons, we performed uplift testing designed to assess whether use of Llama 3.1 models could meaningfully increase the capabilities of malicious actors to plan or carry out attacks using these types of weapons. For Llama 3.2-Vision models, we conducted additional targeted evaluations and found that it was unlikely Llama 3.2 presented an increase in scientific capabilities due to its added image understanding capability as compared to Llama 3.1.
+
+**2\. Child Safety:** Child Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development.  For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors including the additional languages Llama 3 is trained on. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.  
+
+**3\. Cyber Attacks:** For Llama 3.1 405B, our cyber attack uplift study investigated whether LLMs can enhance human capabilities in hacking tasks, both in terms of skill level and speed.
+Our attack automation study focused on evaluating the capabilities of LLMs when used as autonomous agents in cyber offensive operations, specifically in the context of ransomware attacks. This evaluation was distinct from previous studies that considered LLMs as interactive assistants. The primary objective was to assess whether these models could effectively function as independent agents in executing complex cyber-attacks without human intervention. Because Llama 3.2’s vision capabilities are not generally germane to cyber uplift, we believe that the testing conducted for Llama 3.1 also applies to Llama 3.2.
+
+### Community 
+
+**Industry Partnerships:** Generative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership on AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our [Github repository](https://github.com/meta-llama/PurpleLlama).
+
+**Grants:** We also set up the [Llama Impact Grants](https://llama.meta.com/llama-impact-grants/) program to identify and support the most compelling applications of Meta’s Llama model for societal benefit across three categories: education, climate and open innovation. The 20 finalists from the hundreds of applications can be found [here](https://llama.meta.com/llama-impact-grants/#finalists). 
+
+**Reporting:** Finally, we put in place a set of resources including an [output reporting mechanism](https://developers.facebook.com/llama_output_feedback) and [bug bounty program](https://www.facebook.com/whitehat) to continuously improve the Llama technology with the help of the community.
+
+## Ethical Considerations and Limitations
+
+**Values:** The core values of Llama 3.2 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3.2 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress. 
+
+**Testing:** But Llama 3.2 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3.2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3.2 models, developers should perform safety testing and tuning tailored to their specific applications of the model. Please refer to available resources including our [Responsible Use Guide](https://llama.meta.com/responsible-use-guide), [Trust and Safety](https://llama.meta.com/trust-and-safety/) solutions, and other [resources](https://llama.meta.com/docs/get-started/) to learn more about responsible development.   

USE_POLICY.md

@@ -0,0 +1,52 @@
+**Llama 3.2** **Acceptable Use Policy**
+
+Meta is committed to promoting safe and fair use of its tools and features, including Llama 3.2. If you access or use Llama 3.2, you agree to this Acceptable Use Policy (“**Policy**”). The most recent copy of this policy can be found at [https://www.llama.com/llama3_2/use-policy](https://www.llama.com/llama3_2/use-policy).
+
+**Prohibited Uses**
+
+We want everyone to use Llama 3.2 safely and responsibly. You agree you will not use, or allow others to use, Llama 3.2 to:
+
+
+
+1. Violate the law or others’ rights, including to:
+    1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:
+        1. Violence or terrorism
+        2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material
+        3. Human trafficking, exploitation, and sexual violence
+        4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.
+        5. Sexual solicitation
+        6. Any other criminal activity
+    1. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals
+    2. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services
+    3. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices
+    4. Collect, process, disclose, generate, or infer private or sensitive information about individuals, including information about individuals’ identity, health, or demographic information, unless you have obtained the right to do so in accordance with applicable law
+    5. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials
+    6. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system
+    7. Engage in any action, or facilitate any action, to intentionally circumvent or remove usage restrictions or other safety measures, or to enable functionality disabled by Meta 
+2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Llama 3.2 related to the following:
+    8. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State or to the U.S. Biological Weapons Anti-Terrorism Act of 1989 or the Chemical Weapons Convention Implementation Act of 1997
+    9. Guns and illegal weapons (including weapon development)
+    10. Illegal drugs and regulated/controlled substances
+    11. Operation of critical infrastructure, transportation technologies, or heavy machinery
+    12. Self-harm or harm to others, including suicide, cutting, and eating disorders
+    13. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual
+3. Intentionally deceive or mislead others, including use of Llama 3.2 related to the following:
+    14. Generating, promoting, or furthering fraud or the creation or promotion of disinformation
+    15. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content
+    16. Generating, promoting, or further distributing spam
+    17. Impersonating another individual without consent, authorization, or legal right
+    18. Representing that the use of Llama 3.2 or outputs are human-generated
+    19. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement 
+4. Fail to appropriately disclose to end users any known dangers of your AI system
+5. Interact with third party tools, models, or software designed to generate unlawful content or engage in unlawful or harmful conduct and/or represent that the outputs of such tools, models, or software are associated with Meta or Llama 3.2
+
+With respect to any multimodal models included in Llama 3.2, the rights granted under Section 1(a) of the Llama 3.2 Community License Agreement are not being granted to you if you are an individual domiciled in, or a company with a principal place of business in, the European Union. This restriction does not apply to end users of a product or service that incorporates any such multimodal models.
+
+Please report any violation of this Policy, software “bug,” or other problems that could lead to a violation of this Policy through one of the following means:
+
+
+
+* Reporting issues with the model: [https://github.com/meta-llama/llama-models/issues](https://l.workplace.com/l.php?u=https%3A%2F%2Fgithub.com%2Fmeta-llama%2Fllama-models%2Fissues&h=AT0qV8W9BFT6NwihiOHRuKYQM_UnkzN_NmHMy91OT55gkLpgi4kQupHUl0ssR4dQsIQ8n3tfd0vtkobvsEvt1l4Ic6GXI2EeuHV8N08OG2WnbAmm0FL4ObkazC6G_256vN0lN9DsykCvCqGZ)
+* Reporting risky content generated by the model: [developers.facebook.com/llama_output_feedback](http://developers.facebook.com/llama_output_feedback)
+* Reporting bugs and security concerns: [facebook.com/whitehat/info](http://facebook.com/whitehat/info)
+* Reporting violations of the Acceptable Use Policy or unlicensed uses of Llama 3.2: LlamaUseReport@meta.com

adapter_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50bab6631f3c150dd1fef0b9902821c428aaa0b1268047da4d35a3f56ff5909b
+size 62546298

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,222 @@
+{
+  "architectures": [
+    "MllamaForConditionalGeneration"
+  ],
+  "image_token_index": 128256,
+  "model_type": "mllama",
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 128000,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "cross_attention_layers": [
+      3,
+      8,
+      13,
+      18,
+      23,
+      28,
+      33,
+      38
+    ],
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": [
+      128001,
+      128008,
+      128009
+    ],
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 131072,
+    "min_length": 0,
+    "model_type": "mllama_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 128004,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": {
+      "factor": 8.0,
+      "high_freq_factor": 4.0,
+      "low_freq_factor": 1.0,
+      "original_max_position_embeddings": 8192,
+      "rope_type": "llama3"
+    },
+    "rope_theta": 500000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 128256
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_heads": 16,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 560,
+    "intermediate_layers_indices": [
+      3,
+      7,
+      15,
+      23,
+      30
+    ],
+    "intermediate_size": 5120,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_num_tiles": 4,
+    "min_length": 0,
+    "model_type": "mllama_vision_model",
+    "no_repeat_ngram_size": 0,
+    "norm_eps": 1e-05,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_global_layers": 8,
+    "num_hidden_layers": 32,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "supported_aspect_ratios": [
+      [
+        1,
+        1
+      ],
+      [
+        1,
+        2
+      ],
+      [
+        1,
+        3
+      ],
+      [
+        1,
+        4
+      ],
+      [
+        2,
+        1
+      ],
+      [
+        2,
+        2
+      ],
+      [
+        3,
+        1
+      ],
+      [
+        4,
+        1
+      ]
+    ],
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vision_output_dim": 7680
+  }
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
+}

hf_model_0001_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1494c7b8dd0ac7ee53d4b0e0541756cb0ad7f77cfe01b51907fa19f92156f706
+size 4992741022

hf_model_0002_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10d5629b1dfac986e49271965b3f536b4dffe19896f7c0ffb6fc14ad78b6fad7
+size 4966275300

hf_model_0003_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7b209965cf5aa68b802a8a6a21ae64048bc4f69c3d6d3809312300a8da0975
+size 4915942578

hf_model_0004_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:585338bfce16d3f209eccb4b128f4988f5b1454878d97fe5b26c2402213cbd06
+size 4999848966

hf_model_0005_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dfe25c2e955d84971042902ea4aebaac6a8ff0a104b0484bfccbd685d4bccb1
+size 1465945700

logs/log_1732912200.txt

@@ -0,0 +1 @@
+Step 1 | loss:1.566798210144043 lr:1.0000000000000002e-06 tokens_per_second_per_gpu:49.94605255126953 grad_norm:3.15625 

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d183d799f0476061adc580ccc0a24abba5ab274d610f02e73aff7576e581118c
+size 4992622346

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a7afac7fbc248a8b038709ec3fb5bae4e5588ea84130056c8ed4e5a5144b40
+size 4966251712

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24149e6a1922551067d64d78d8a41ac8393e502d6b64f551a4f73bbacbb5bf90
+size 4915919704

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caf17798db8a5de475bc7580706956032533cd7a9dfb588ad8488229c745bbad
+size 4999823980

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656566a9aeee1115ca174c16ea3c51a2839b3a7f14cc349805aa0ef5c7433e7b
+size 1465943128

model.safetensors.index.json

@@ -0,0 +1,913 @@
+{
+  "metadata": {
+    "total_size": 21340441670
+  },
+  "weight_map": {
+    "language_model.lm_head.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.k_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.q_norm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn_attn_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.cross_attn_mlp_gate": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.k_norm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.q_norm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn_attn_gate": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.cross_attn_mlp_gate": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.37.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.k_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.q_norm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn_attn_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.cross_attn_mlp_gate": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.38.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.39.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "language_model.model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.k_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.q_norm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn_attn_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.cross_attn_mlp_gate": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "language_model.model.norm.weight": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.bias": "model-00005-of-00005.safetensors",
+    "multi_modal_projector.weight": "model-00005-of-00005.safetensors",
+    "vision_model.class_embedding": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.embedding": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.gated_positional_embedding.tile_embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.gate_attn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.gate_ffn": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.global_transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_post.weight": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.bias": "model-00001-of-00005.safetensors",
+    "vision_model.layernorm_pre.weight": "model-00001-of-00005.safetensors",
+    "vision_model.patch_embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.post_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.post_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.pre_tile_positional_embedding.embedding.weight": "model-00001-of-00005.safetensors",
+    "vision_model.pre_tile_positional_embedding.gate": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc1.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc1.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc2.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.mlp.fc2.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.post_attention_layernorm.bias": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "vision_model.transformer.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors"
+  }
+}

original/params.json

@@ -0,0 +1,15 @@
+{
+  "dim": 4096,
+  "ffn_dim_multiplier": 1.3,
+  "multiple_of": 1024,
+  "n_heads": 32,
+  "n_kv_heads": 8,
+  "n_layers": 32,
+  "norm_eps": 1e-05,
+  "rope_theta": 500000.0,
+  "use_scaled_rope": true,
+  "vision_chunk_size": 560,
+  "vision_max_num_chunks": 4,
+  "vocab_size": 128256,
+  "vision_num_cross_attention_layers": 8
+}

original/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82e9d31979e92ab929cd544440f129d9ecd797b69e327f80f17e1c50d5551b55
+size 2183982

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "MllamaImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_image_tiles": 4,
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 560,
+    "width": 560
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,2071 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|step_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- for content in message['content'] %}\n        {%- if content['type'] == 'image' %}\n            {%- set image_ns.has_images = true %}\n        {%- endif %}\n    {%- endfor %}\n{%- endfor %}\n\n{#- Error out if there are images and system message #}\n{%- if image_ns.has_images and not system_message == \"\" %}\n    {{- raise_exception(\"Prompting with images is incompatible with system messages.\") }}\n{%- endif %}\n\n{#- System message if there are no images #}\n{%- if not image_ns.has_images %}\n    {{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n    {%- if tools is not none %}\n        {{- \"Environment: ipython\\n\" }}\n    {%- endif %}\n    {{- \"Cutting Knowledge Date: December 2023\\n\" }}\n    {{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n    {%- if tools is not none and not tools_in_user_message %}\n        {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n        {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n        {{- \"Do not use variables.\\n\\n\" }}\n        {%- for t in tools %}\n            {{- t | tojson(indent=4) }}\n            {{- \"\\n\\n\" }}\n        {%- endfor %}\n    {%- endif %}\n    {{- system_message }}\n    {{- \"<|eot_id|>\" }}\n{%- endif %}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

torchtune_config.yaml

@@ -0,0 +1,76 @@
+model:
+  _component_: torchtune.models.llama3_2_vision.qlora_llama3_2_vision_11b
+  decoder_trainable: frozen
+  encoder_trainable: lora
+  fusion_trainable: lora
+  lora_attn_modules:
+  - q_proj
+  - v_proj
+  - output_proj
+  apply_lora_to_mlp: true
+  apply_lora_to_output: false
+  lora_rank: 8
+  lora_alpha: 16
+  lora_dropout: 0.0
+  image_size: 560
+tokenizer:
+  _component_: torchtune.models.llama3_2_vision.llama3_2_vision_transform
+  path: /tmp/Llama-3.2-11B-Vision-Instruct/original/tokenizer.model
+  image_size: 560
+  max_seq_len: 8192
+checkpointer:
+  _component_: torchtune.training.FullModelHFCheckpointer
+  checkpoint_dir: /tmp/Llama-3.2-11B-Vision-Instruct/
+  checkpoint_files:
+    filename_format: model-{}-of-{}.safetensors
+    max_filename: '00005'
+  recipe_checkpoint: null
+  output_dir: /tmp/Llama-3.2-11B-Vision-Instruct/
+  model_type: LLAMA3_VISION
+resume_from_checkpoint: false
+save_adapter_weights_only: false
+dataset:
+  _component_: torchtune.datasets.multimodal.the_cauldron_dataset
+  subset: diagram_image_to_text
+seed: null
+shuffle: true
+collate_fn: torchtune.data.padded_collate_tiled_images_and_mask
+epochs: 1
+max_steps_per_epoch: null
+batch_size: 2
+gradient_accumulation_steps: 8
+optimizer:
+  _component_: torch.optim.AdamW
+  fused: true
+  weight_decay: 0.01
+  lr: 0.0001
+lr_scheduler:
+  _component_: torchtune.training.lr_schedulers.get_cosine_schedule_with_warmup
+  num_warmup_steps: 100
+loss:
+  _component_: torchtune.modules.loss.CEWithChunkedOutputLoss
+clip_grad_norm: 1.0
+compile: false
+device: cuda
+enable_activation_checkpointing: true
+dtype: bf16
+output_dir: /tmp/qlora-llama3.2-vision-finetune
+metric_logger:
+  _component_: torchtune.training.metric_logging.WandBLogger
+  project: llama-3.2-vlm-torchtune
+log_every_n_steps: 1
+log_peak_memory_stats: true
+profiler:
+  _component_: torchtune.training.setup_torch_profiler
+  enabled: false
+  output_dir: ${output_dir}/profiling_outputs
+  cpu: true
+  cuda: true
+  profile_memory: false
+  with_stack: false
+  record_shapes: true
+  with_flops: false
+  wait_steps: 5
+  warmup_steps: 3
+  active_steps: 2
+  num_cycles: 1