Improve model card for LoRA adapters

README.md

@@ -1,200 +1,131 @@
 ---
 library_name: transformers
-tags: []
+pipeline_tag: text-generation
+tags:
+- lora
+license: cc-by-nc-4.0
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
-
+# Model Card for LoRA Adapters
 
+This model card describes LoRA adapters fine-tuned from Llama-3.1-8B-Instruct to incorporate new knowledge while trying to maintain previously learned information. It explores the limitations of LoRA-based LLM updates.
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+*   **Developed by:** [Sergey Pletenev, Maria Marina, Daniil Moskovskiy, Vasily Konovalov, Pavel Braslavski, Alexander Panchenko, Mikhail Salnikov]
+*   **Model type:** Causal language model, LoRA adapters
+*   **Language(s) (NLP):** English
+*   **License:** CC-BY-NC-4.0
+*   **Finetuned from model:** [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct)
 
-- **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
 
-### Model Sources [optional]
-
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+*   **Repository:** This repository.
+*   **Paper:** [How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?](https://arxiv.org/abs/2502.14502)
 
 ## 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]
+These LoRA adapters are intended to be used with the base Llama-3.1-8B-Instruct model for text generation tasks, particularly in scenarios where incorporating new knowledge is desired.
 
-### Downstream Use [optional]
+### Downstream Use
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
+These LoRA adapters can be integrated into question-answering systems, chatbots, or other applications that require up-to-date information. However, caution is advised due to potential performance degradation on external question-answering benchmarks and a tendency towards biased answers.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+The model should not be used in applications where biased or inaccurate information could have serious consequences, such as medical or legal advice.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+The model exhibits the following biases, risks, and limitations:
 
-[More Information Needed]
+*   **Performance Degradation:** Performance on external question-answering benchmarks may decline after fine-tuning.
+*   **Answer Bias:** The model may regress to few overrepresented answers when the training data is biased towards certain entities.
+*   **Overconfidence:** The model becomes more confident and may refuse to provide an answer in fewer cases, even when uncertain.
 
 ### 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.
+Users should be aware of the risks, biases, and limitations of the model. When incorporating new knowledge, ensure that the training data contains a balanced mixture of known and new facts. Carefully tune parameters to balance new knowledge integration and general model capabilities.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+1.  Install the necessary libraries:
 
-[More Information Needed]
+```bash
+pip install transformers peft accelerate
+```
 
-## Training Details
+2.  Load the base model and LoRA adapter:
 
-### Training Data
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
 
-<!-- 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. -->
+model_name = "meta-llama/Meta-Llama-3.1-8B-Instruct"
+adapter_name = "YOUR_ADAPTER_NAME"  # Replace with the actual adapter name
 
-[More Information Needed]
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype=torch.float16)
+model = PeftModel.from_pretrained(model, adapter_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
 
-### Training Procedure
+model.eval()
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+prompt = "What is the capital of France?"
+input_ids = tokenizer(prompt, return_tensors="pt").to(model.device)
 
-#### Preprocessing [optional]
+with torch.no_grad():
+    outputs = model.generate(**input_ids, max_new_tokens=50)
 
-[More Information Needed]
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
 
+## Training Details
 
-#### Training Hyperparameters
+### Training Data
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+The model was fine-tuned using LoRA on the base Llama-3.1-8B-instruct model. The training data consists of a mixture of known and new facts. The new facts were created using a head-to-tail pipeline, generating questions and answers using templates and information extracted from a Dbpedia dump.
 
-#### Speeds, Sizes, Times [optional]
+### Training Procedure
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+The model was trained using LoRA (Low-Rank Adaptation). The training data composition and tuning parameters are crucial for balancing new knowledge integration and general model capabilities.
 
-[More Information Needed]
+#### Training Hyperparameters
 
-## Evaluation
+*   **Training regime:** LoRA fine-tuning
+*   **Base Model:** Llama-3.1-8B-instruct
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+## Evaluation
 
 ### 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]
+*   **Testing Data:** External question-answering benchmarks were used to evaluate the model's performance on previously learned knowledge.
+*   **Metrics:** The primary metric was accuracy on the question-answering benchmarks. Additionally, the model's confidence and refusal rate were analyzed.
 
 ### Results
 
-[More Information Needed]
+Experiments have shown that fine-tuning with LoRA can lead to a decline in performance on external question-answering benchmarks. The best results are obtained when the training data contains a mixture of known and new facts, but this approach is still potentially harmful.
 
 #### Summary
 
+The model's performance is sensitive to the composition of the training data. Fine-tuning with biased data can lead to a regression towards overrepresented answers and a decline in overall performance.
 
+## Citation
 
-## 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]
-
-arxiv.org/abs/2502.14502
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+[How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?](https://arxiv.org/abs/2502.14502)
 
 **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]
+```
+@misc{pletenev2025knowledgepackloraadapter,
+      title={How Much Knowledge Can You Pack into a LoRA Adapter without Harming LLM?}, 
+      author={Sergey Pletenev and Maria Marina and Daniil Moskovskiy and Vasily Konovalov and Pavel Braslavski and Alexander Panchenko and Mikhail Salnikov},
+      year={2025},
+      eprint={2502.14502},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2502.14502}, 
+}
+```