Upload 13 files

environment.yml

@@ -0,0 +1,252 @@
+name: aspdac24
+channels:
+  - dglteam/label/cu117
+  - conda-forge
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=conda_forge
+  - _openmp_mutex=4.5=2_gnu
+  - at-spi2-atk=2.38.0=h0630a04_3
+  - at-spi2-core=2.40.3=h0630a04_0
+  - atk-1.0=2.38.0=hd4edc92_1
+  - brotli=1.1.0=hd590300_1
+  - brotli-bin=1.1.0=hd590300_1
+  - brotli-python=1.0.9=py311h6a678d5_7
+  - bzip2=1.0.8=h7b6447c_0
+  - ca-certificates=2023.12.12=h06a4308_0
+  - cairo=1.16.0=hb05425b_5
+  - cairomm-1.16=1.16.2=h7e731d7_1
+  - certifi=2023.11.17=py311h06a4308_0
+  - cffi=1.16.0=py311hb3a22ac_0
+  - contourpy=1.2.0=py311h9547e67_0
+  - cryptography=41.0.7=py311hdda0065_0
+  - cycler=0.12.1=pyhd8ed1ab_0
+  - dbus=1.13.6=h5008d03_3
+  - dgl=1.1.2.cu117=py311_0
+  - epoxy=1.5.10=h166bdaf_1
+  - expat=2.5.0=hcb278e6_1
+  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
+  - font-ttf-inconsolata=3.000=h77eed37_0
+  - font-ttf-source-code-pro=2.038=h77eed37_0
+  - font-ttf-ubuntu=0.83=h77eed37_1
+  - fontconfig=2.14.1=h4c34cd2_2
+  - fonts-conda-ecosystem=1=0
+  - fonts-conda-forge=1=0
+  - fonttools=4.46.0=py311h459d7ec_0
+  - freetype=2.12.1=h267a509_2
+  - fribidi=1.0.10=h36c2ea0_0
+  - gdk-pixbuf=2.42.10=h6c15284_3
+  - gettext=0.21.1=h27087fc_0
+  - glib=2.78.3=hfc55251_0
+  - glib-tools=2.78.3=hfc55251_0
+  - gmp=6.3.0=h59595ed_0
+  - graph-tool=2.58=py311h35b2f40_2
+  - graph-tool-base=2.58=py311h2a117df_2
+  - graphite2=1.3.14=h295c915_1
+  - gtk3=3.24.34=h13ada96_0
+  - harfbuzz=4.3.0=hf52aaf7_2
+  - hicolor-icon-theme=0.17=ha770c72_2
+  - icu=73.2=h59595ed_0
+  - keyutils=1.6.1=h166bdaf_0
+  - kiwisolver=1.4.5=py311h9547e67_1
+  - krb5=1.21.2=h659d440_0
+  - lcms2=2.15=h7f713cb_2
+  - ld_impl_linux-64=2.38=h1181459_1
+  - lerc=4.0.0=h27087fc_0
+  - libblas=3.9.0=20_linux64_openblas
+  - libboost=1.82.0=h6fcfa73_6
+  - libboost-python=1.82.0=py311h92ebd52_6
+  - libbrotlicommon=1.1.0=hd590300_1
+  - libbrotlidec=1.1.0=hd590300_1
+  - libbrotlienc=1.1.0=hd590300_1
+  - libcblas=3.9.0=20_linux64_openblas
+  - libcups=2.3.3=h4637d8d_4
+  - libdeflate=1.19=hd590300_0
+  - libedit=3.1.20191231=he28a2e2_2
+  - libexpat=2.5.0=hcb278e6_1
+  - libffi=3.4.4=h6a678d5_0
+  - libgcc-ng=13.2.0=h807b86a_3
+  - libgfortran-ng=13.2.0=h69a702a_3
+  - libgfortran5=13.2.0=ha4646dd_3
+  - libgirepository=1.78.1=h003a4f0_1
+  - libglib=2.78.3=h783c2da_0
+  - libgomp=13.2.0=h807b86a_3
+  - libiconv=1.17=hd590300_1
+  - libjpeg-turbo=2.1.5.1=hd590300_1
+  - liblapack=3.9.0=20_linux64_openblas
+  - libopenblas=0.3.25=pthreads_h413a1c8_0
+  - libpng=1.6.39=h753d276_0
+  - librsvg=2.54.4=h7abd40a_0
+  - libstdcxx-ng=13.2.0=h7e041cc_3
+  - libtiff=4.6.0=h29866fb_1
+  - libuuid=1.41.5=h5eee18b_0
+  - libwebp-base=1.3.2=hd590300_0
+  - libxcb=1.15=h0b41bf4_0
+  - libxml2=2.10.4=hf1b16e4_1
+  - libzlib=1.2.13=hd590300_5
+  - matplotlib-base=3.8.0=py311h54ef318_1
+  - munkres=1.1.4=pyh9f0ad1d_0
+  - ncurses=6.4=h6a678d5_0
+  - numpy=1.26.2=py311h64a7726_0
+  - openjpeg=2.5.0=h488ebb8_3
+  - openssl=3.2.0=hd590300_1
+  - packaging=23.2=pyhd8ed1ab_0
+  - pango=1.50.7=hbd2fdc8_0
+  - pcre2=10.42=hcad00b1_0
+  - pillow=10.0.1=py311h8aef010_1
+  - pip=23.3.1=py311h06a4308_0
+  - pixman=0.42.2=h59595ed_0
+  - pthread-stubs=0.4=h36c2ea0_1001
+  - pycairo=1.25.0=py311h8feb60e_1
+  - pycparser=2.21=pyhd8ed1ab_0
+  - pygobject=3.46.0=py311h86ed371_1
+  - pyopenssl=23.2.0=py311h06a4308_0
+  - pyparsing=3.1.1=pyhd8ed1ab_0
+  - pysocks=1.7.1=py311h06a4308_0
+  - python=3.11.5=h955ad1f_0
+  - python-dateutil=2.8.2=pyhd8ed1ab_0
+  - python_abi=3.11=2_cp311
+  - readline=8.2=h5eee18b_0
+  - requests=2.31.0=py311h06a4308_0
+  - scipy=1.11.4=py311h64a7726_0
+  - setuptools=68.2.2=py311h06a4308_0
+  - sigcpp-3.0=3.6.0=h59595ed_0
+  - six=1.16.0=pyh6c4a22f_0
+  - sparsehash=2.0.4=hcb278e6_1
+  - sqlite=3.41.2=h5eee18b_0
+  - tk=8.6.12=h1ccaba5_0
+  - wheel=0.41.2=py311h06a4308_0
+  - xorg-fixesproto=5.0=h7f98852_1002
+  - xorg-inputproto=2.3.2=h7f98852_1002
+  - xorg-kbproto=1.0.7=h7f98852_1002
+  - xorg-libx11=1.8.7=h8ee46fc_0
+  - xorg-libxau=1.0.11=hd590300_0
+  - xorg-libxdmcp=1.1.3=h7f98852_0
+  - xorg-libxext=1.3.4=h0b41bf4_2
+  - xorg-libxfixes=5.0.3=h7f98852_1004
+  - xorg-libxi=1.7.10=h7f98852_0
+  - xorg-libxtst=1.2.3=h7f98852_1002
+  - xorg-recordproto=1.14.2=h7f98852_1002
+  - xorg-xextproto=7.3.0=h0b41bf4_1003
+  - xorg-xproto=7.0.31=h7f98852_1007
+  - xz=5.4.5=h5eee18b_0
+  - zlib=1.2.13=hd590300_5
+  - zstandard=0.22.0=py311haa97af0_0
+  - zstd=1.5.5=hfc55251_0
+  - pip:
+      - accelerate==0.27.2
+      - aiohttp==3.9.3
+      - aiosignal==1.3.1
+      - annotated-types==0.6.0
+      - anyio==4.3.0
+      - attrs==23.1.0
+      - beautifulsoup4==4.12.2
+      - bitsandbytes==0.42.0
+      - bleach==6.1.0
+      - chardet==5.2.0
+      - charset-normalizer==3.3.2
+      - datasets==2.16.1
+      - deepspeed==0.13.4
+      - defusedxml==0.7.1
+      - dill==0.3.7
+      - distro==1.9.0
+      - docstring-parser==0.15
+      - einops==0.7.0
+      - et-xmlfile==1.1.0
+      - fairscale==0.4.13
+      - fastjsonschema==2.19.1
+      - filelock==3.13.1
+      - fire==0.5.0
+      - flash-attn==2.5.5
+      - frozenlist==1.4.1
+      - fsspec==2023.10.0
+      - h11==0.14.0
+      - hjson==3.1.0
+      - httpcore==1.0.4
+      - httpx==0.27.0
+      - huggingface-hub==0.20.3
+      - idna==3.6
+      - jinja2==3.1.2
+      - joblib==1.3.2
+      - jsonlines==4.0.0
+      - jsonschema==4.20.0
+      - jsonschema-specifications==2023.12.1
+      - jupyter-client==8.6.0
+      - jupyter-core==5.5.1
+      - jupyterlab-pygments==0.3.0
+      - markdown-it-py==3.0.0
+      - markupsafe==2.1.3
+      - mdurl==0.1.2
+      - mistune==3.0.2
+      - mpmath==1.3.0
+      - multidict==6.0.5
+      - multiprocess==0.70.15
+      - nbclient==0.9.0
+      - nbconvert==7.13.1
+      - nbformat==5.9.2
+      - networkx==3.2.1
+      - ninja==1.11.1.1
+      - nvidia-cublas-cu11==11.10.3.66
+      - nvidia-cublas-cu12==12.1.3.1
+      - nvidia-cuda-cupti-cu12==12.1.105
+      - nvidia-cuda-nvrtc-cu11==11.7.99
+      - nvidia-cuda-nvrtc-cu12==12.1.105
+      - nvidia-cuda-runtime-cu11==11.7.99
+      - nvidia-cuda-runtime-cu12==12.1.105
+      - nvidia-cudnn-cu11==8.5.0.96
+      - nvidia-cudnn-cu12==8.9.2.26
+      - nvidia-cufft-cu12==11.0.2.54
+      - nvidia-curand-cu12==10.3.2.106
+      - nvidia-cusolver-cu12==11.4.5.107
+      - nvidia-cusparse-cu12==12.1.0.106
+      - nvidia-nccl-cu12==2.19.3
+      - nvidia-nvjitlink-cu12==12.3.101
+      - nvidia-nvtx-cu12==12.1.105
+      - openai==1.13.3
+      - openpyxl==3.1.2
+      - pandas==2.1.4
+      - pandocfilters==1.5.0
+      - peft==0.8.2
+      - platformdirs==4.1.0
+      - protobuf==4.25.2
+      - psutil==5.9.7
+      - py-cpuinfo==9.0.0
+      - pyarrow==15.0.0
+      - pyarrow-hotfix==0.6
+      - pydantic==2.6.2
+      - pydantic-core==2.16.3
+      - pygments==2.17.2
+      - pynvml==11.5.0
+      - pytz==2023.3.post1
+      - pyyaml==6.0.1
+      - pyzmq==25.1.2
+      - referencing==0.32.0
+      - regex==2023.12.25
+      - rich==13.7.0
+      - rpds-py==0.16.2
+      - safetensors==0.4.2
+      - scikit-learn==1.3.2
+      - sentencepiece==0.1.99
+      - shtab==1.6.5
+      - sniffio==1.3.1
+      - soupsieve==2.5
+      - sympy==1.12
+      - termcolor==2.4.0
+      - threadpoolctl==3.2.0
+      - tinycss2==1.2.1
+      - tokenizers==0.15.1
+      - torch==2.2.1
+      - tornado==6.4
+      - tqdm==4.66.1
+      - traitlets==5.14.0
+      - transformers==4.38.1
+      - triton==2.2.0
+      - trl==0.7.11
+      - typing-extensions==4.9.0
+      - tyro==0.7.2
+      - tzdata==2023.3
+      - urllib3==2.1.0
+      - webencodings==0.5.1
+      - xxhash==3.4.1
+      - yarl==1.9.4
+prefix: /home/bingyuew/miniconda3/envs/aspdac24

example.py

@@ -0,0 +1,52 @@
+##########################
+#Must include these lines#
+##########################
+import os
+os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID"
+os.environ["CUDA_VISIBLE_DEVICES"]="0,1,2,3"
+import torch
+from transformers import (
+  AutoModelForCausalLM,
+  AutoTokenizer,
+  pipeline,
+)
+from peft import PeftModel
+
+####################################################
+#This is how you can set up Llama model on your end#
+####################################################
+model = AutoModelForCausalLM.from_pretrained(
+  'codellama/CodeLlama-7b-Instruct-hf',
+  device_map = "balanced_low_0"
+)
+
+tokenizer = AutoTokenizer.from_pretrained(
+  'llama_prompt_model/tokenizer',
+  padding=True,
+  truncation=True,
+  device_map = "balanced_low_0"
+)
+
+model.resize_token_embeddings(len(tokenizer))
+
+model = PeftModel.from_pretrained(model, "llama_prompt_model/model")
+
+model = model.merge_and_unload()
+
+################################################
+#This is how you can communicate with the model#
+################################################
+pipe = pipeline(task="text-generation", model = model, tokenizer = tokenizer, max_length = 2000, pad_token_id = 2)
+
+##################################################
+#feel free to change this line and see the result#
+##################################################
+prompt = "What's your name?"
+
+result = pipe("<s>[INST]%s[/INST]"%(prompt))[0]['generated_text']
+
+print(result)
+
+
+
+

llama_prompt_model/model/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: codellama/CodeLlama-7b-Instruct-hf
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.8.2

llama_prompt_model/model/adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

llama_prompt_model/model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d172f45a8d554d8da745a5d1c6f493b98885f45617cba57fa325cc6e4b0e14
+size 844476320

llama_prompt_model/model/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.1",
+  "use_cache": false,
+  "vocab_size": 32019
+}

llama_prompt_model/model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.1"
+}

llama_prompt_model/model/model.safetensors.index.json

@@ -0,0 +1,746 @@
+{
+  "metadata": {
+    "total_size": 13796958208
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

llama_prompt_model/tokenizer/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</CPP>": 32018,
+  "<CPP>": 32017,
+  "<MASK>": 32016
+}

llama_prompt_model/tokenizer/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<MASK>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

llama_prompt_model/tokenizer/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

llama_prompt_model/tokenizer/tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<MASK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<CPP>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "</CPP>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "device_map": "balanced_low_0",
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "mask_token": "<MASK>",
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding": true,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "truncation": true,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}