OctaSpace
/

Mistral7B-fintuned-multi_x_science

Safetensors

Model card Files Files and versions Community

tdelic commited on Feb 13

Commit

d6258ee

•

1 Parent(s): 57bb9a8

Upload README.md

Browse files

Files changed (1) hide show

README.md +122 -203

README.md CHANGED Viewed

@@ -1,204 +1,123 @@
----
-library_name: peft
-base_model: mistral7b
----
-# Model Card for Model ID
-Mistral7B fintunded on Multi-XScience dataset, which a more specialized vocabulary in science and more capacity in the scientific conversation summary task.
-## 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 0.7.1

+  # Fine-tuned Mistral Model for Multi-Document Summarization
+  This model a fine-tuned model based on [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on
+   [multi_x_science_sum](https://huggingface.co/datasets/multi_x_science_sum) dataset.
+  ## Model description
+Mistral-7B-multixscience-finetuned is finetuned on multi_x_science_sum
+dataset in order to extend the capabilities of the original
+Mistral model in multi-document summarization tasks.
+The fine-tuned model leverages the power of Mistral model fundation,
+adapting it to synthesize and summarize information from
+multiple documents efficiently.
+## Training and evaluation dataset
+Multi_x_science_sum is a large-scale multi-document
+summarization dataset created from scientific articles.
+Multi-XScience introduces a challenging multi-document
+summarization task: writing the related-work section of a
+paper based on its abstract and the articles it references.
+* [paper](https://arxiv.org/pdf/2010.14235.pdf)
+* [Source](https://huggingface.co/datasets/multi_x_science_sum)
+The training and evaluation datasets were uniquely generated
+to facilitate the fine-tuning of the model for
+multi-document summarization, particularly focusing on
+generating related work sections for scientific papers.
+Using a custom-designed prompt-generation process, the dataset
+is created to simulate the task of synthesizing related work
+sections based on a given paper's abstract and the abstracts
+of its referenced papers.
+### Dataset Generation process
+The process involves generating prompts that instruct the
+model to use the abstract of the current paper along with
+the abstracts of cited papers to generate a new related work
+section. This approach aims to mimic the real-world scenario
+where a researcher synthesizes information from multiple
+sources to draft the related work section of a paper.
+* **Prompt Structure:** Each data point consists of an instructional prompt that includes:
+  * The abstract of the current paper.
+  * Abstracts from cited papers, labeled with unique identifiers.
+  * An expected model response in the form of a generated related work section.
+### Prompt generation Code
+```
+def generate_related_work_prompt(data):
+    prompt = "[INST] <<SYS>>\n"
+    prompt += "Use the abstract of the current paper and the abstracts of the cited papers to generate new related work.\n"
+    prompt += "<</SYS>>\n\n"
+    prompt += "Input:\nCurrent Paper's Abstract:\n- {}\n\n".format(data['abstract'])
+    prompt += "Cited Papers' Abstracts:\n"
+    for cite_id, cite_abstract in zip(data['ref_abstract']['cite_N'], data['ref_abstract']['abstract']):
+        prompt += "- {}: {}\n".format(cite_id, cite_abstract)
+    prompt += "\n[/INST]\n\nGenerated Related Work:\n{}\n".format(data['related_work'])
+    return {"text": prompt}
+```
+The dataset generated through this process was used to train
+and evaluate the finetuned model, ensuring that it learns to
+accurately synthesize information from multiple sources into
+cohesive summaries.
+## Training hyperparameters
+The following hyperparameters were used during training:
+```
+learning_rate: 2e-5
+train_batch_size: 4
+eval_batch_size: 4
+seed: 42
+optimizer: adamw_8bit
+num_epochs: 5
+```
+## Usage
+```
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftConfig, PeftModel
+base_model = "mistralai/Mistral-7B-v0.1"
+adapter = "OctaSpace/Mistral7B-fintuned"
+# Load tokenizer
+tokenizer = AutoTokenizer.from_pretrained(
+    base_model,
+    add_bos_token=True,
+    trust_remote_code=True,
+    padding_side='left'
+)
+# Create peft model using base_model and finetuned adapter
+config = PeftConfig.from_pretrained(adapter)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path,
+                                             load_in_4bit=True,
+                                             device_map='auto',
+                                             torch_dtype='auto')
+model = PeftModel.from_pretrained(model, adapter)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model.to(device)
+model.eval()
+# Prompt content:
+messages = [] # Put here your related work generation instruction
+input_ids = tokenizer.apply_chat_template(conversation=messages,
+                                          tokenize=True,
+                                          add_generation_prompt=True,
+                                          return_tensors='pt').to(device)
+summary_ids = model.generate(input_ids=input_ids, max_new_tokens=512, do_sample=True, pad_token_id=2)
+summaries = tokenizer.batch_decode(summary_ids.detach().cpu().numpy(), skip_special_tokens = True)
+# Model response:
+print(summaries[0])
+```