Improve model card: Add license, tags, paper, code, project page, and usage example

This PR significantly enhances the model card for `LoRI-S_nlu_llama3_rank_32` by:

- Adding the `license: apache-2.0` to the metadata.
- Including relevant `tags` such as `lora`, `peft`, `nlu`, `code-generation`, `mathematical-reasoning`, `safety-alignment`, and `multi-task-learning` to improve discoverability.
- Updating the main paper link to the Hugging Face Papers page (`https://huggingface.co/papers/2504.07448`).
- Providing a comprehensive description of the LoRI model, its features, and how it addresses cross-task interference.
- Adding direct links to the official GitHub repository (`https://github.com/juzhengz/LoRI/`) and the project page (`https://juzhengz.github.io/`).
- Including a clear Python code snippet for quick inference, making it easier for users to get started.
- Populating various sections such as `Model Details`, `Uses`, `Bias, Risks, and Limitations`, `Training Details`, and `Evaluation` with information extracted from the paper abstract and the GitHub repository's README.
- Adding the academic citation for the paper.
- Embedding an illustrative image from the GitHub repository.

These improvements make the model card much more informative, discoverable, and user-friendly for researchers and practitioners.

README.md

@@ -2,192 +2,189 @@
 base_model: meta-llama/Meta-Llama-3-8B
 library_name: peft
 pipeline_tag: text-generation
+license: apache-2.0
+tags:
+- lora
+- peft
+- nlu
+- code-generation
+- mathematical-reasoning
+- safety-alignment
+- multi-task-learning
 ---
 
 # Model Card for LoRI-S_nlu_llama3_rank_32
 
-This model is part of [LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation](https://arxiv.org/abs/2504.07448).
+This model is part of [LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation](https://huggingface.co/papers/2504.07448).
 
-<!-- Provide a quick summary of what the model is/does. -->
+LoRI (LoRA with Reduced Interference) is a simple yet effective variant of LoRA for fine-tuning Large Language Models (LLMs). It addresses notable overhead and parameter interference in multi-task scenarios by freezing the projection matrices `A` as random projections and sparsifying the matrices `B` using task-specific masks. This design substantially reduces the number of trainable parameters while maintaining strong task performance.
 
+<div align="center">
+    <img src="https://github.com/juzhengz/LoRI/raw/main/LoRI.png" alt="LoRI" width="80%">
+</div>
 
+## Abstract
+
+Low-Rank Adaptation (LoRA) has emerged as a popular parameter-efficient fine-tuning (PEFT) method for Large Language Models (LLMs), yet it still incurs notable overhead and suffers from parameter interference in multi-task scenarios. We propose LoRA with Reduced Interference (LoRI), a simple yet effective approach that freezes the projection matrices $A$ as random projections and sparsifies the matrices $B$ using task-specific masks. This design substantially reduces the number of trainable parameters while maintaining strong task performance. Moreover, LoRI minimizes cross-task interference in adapter merging by leveraging the orthogonality between adapter subspaces, and supports continual learning by using sparsity to mitigate catastrophic forgetting. Extensive experiments across natural language understanding, mathematical reasoning, code generation, and safety alignment tasks demonstrate that LoRI outperforms full fine-tuning and existing PEFT methods, while using up to 95% fewer trainable parameters than LoRA. In multi-task experiments, LoRI enables effective adapter merging and continual learning with reduced cross-task interference. Code is available at: this https URL
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-
+LoRI minimizes cross-task interference in adapter merging by leveraging the orthogonality between adapter subspaces, and supports continual learning by using sparsity to mitigate catastrophic forgetting. This particular model, `LoRI-S_nlu_llama3_rank_32`, is an adapter fine-tuned for Natural Language Understanding (NLU) tasks, based on the Llama-3-8B model with an adapter rank of 32. It is an "LoRI-S" (Sparsified) adapter, indicating it has undergone an additional sparsity-inducing training stage after initial LoRI-D training.
 
-- **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]
+-   **Developed by:** Juzheng Zhang, Jiacheng You, Ashwinee Panda, Tom Goldstein
+-   **Model type:** Low-Rank Adaptation (LoRA) variant, Parameter-Efficient Fine-Tuning (PEFT) method for Causal Language Models
+-   **Language(s) (NLP):** English
+-   **License:** Apache 2.0
+-   **Finetuned from model:** `meta-llama/Meta-Llama-3-8B`
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+-   **Repository:** [https://github.com/juzhengz/LoRI/](https://github.com/juzhengz/LoRI/)
+-   **Paper:** [https://huggingface.co/papers/2504.07448](https://huggingface.co/papers/2504.07448) ([arXiv:2504.07448](https://arxiv.org/abs/2504.07448))
+-   **Project Page:** [https://juzhengz.github.io/](https://juzhengz.github.io/)
+-   **Hugging Face Collection:** [https://huggingface.co/collections/tomg-group-umd/lori-adapters-67f795549d792613e1290011](https://huggingface.co/collections/tomg-group-umd/lori-adapters-67f795549d792613e1290011)
 
 ## 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]
+This model is intended to be used as a PEFT adapter for the `meta-llama/Meta-Llama-3-8B` base model to enhance its performance on Natural Language Understanding tasks. It allows for efficient fine-tuning and deployment of large language models without modifying the original base model's weights.
 
-### 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]
+LoRI adapters are designed to minimize cross-task interference, enabling effective adapter merging for multi-task scenarios and supporting continual learning by mitigating catastrophic forgetting. This makes them suitable for a wide range of downstream applications across NLU, code generation, mathematical reasoning, and safety alignment.
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+As an adapter, this model is not intended for standalone use; it requires a compatible base language model (e.g., `meta-llama/Meta-Llama-3-8B`). Users should also be mindful of the ethical implications and potential biases inherited from the base model and training data when deploying in sensitive applications.
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
+LoRI, like any LLM or PEFT method, may inherit biases present in its foundational `Meta-Llama-3-8B` model and the datasets it was fine-tuned on. While LoRI is designed to reduce cross-task interference and mitigate catastrophic forgetting, these are complex challenges in AI, and complete elimination cannot be guaranteed, especially in highly diverse or long-term continual learning scenarios.
 
 ### 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 perform thorough evaluations for their specific use cases to identify and mitigate potential biases. Continuous monitoring for performance degradation or unintended behaviors is advised, particularly in critical applications. It is recommended to consult the original paper for detailed experimental results and discussions on limitations.
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
+Use the code below to get started with the model using the `transformers` and `peft` libraries. This example demonstrates loading the `LoRI-S_nlu_llama3_rank_32` adapter and performing basic text generation.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+# Load the base model
+base_model_name = "meta-llama/Meta-Llama-3-8B"
+base_model = AutoModelForCausalLM.from_pretrained(
+    base_model_name,
+    torch_dtype=torch.bfloat16, # or torch.float16, depending on your hardware
+    device_map="auto"
+)
+
+# Load the LoRI adapter
+adapter_name = "tomg-group-umd/LoRI-S_nlu_llama3_rank_32" # This specific model
+model = PeftModel.from_pretrained(base_model, adapter_name)
+
+# Load the tokenizer
+tokenizer = AutoTokenizer.from_pretrained(base_model_name)
+
+# Example inference for text generation
+prompt = "The capital of France is"
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+
+output_ids = model.generate(**inputs, max_new_tokens=20, temperature=0.7)
+output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print(output_text)
+
+# Example for chat completion (if the base model supports chat templates)
+# messages = [
+#     {"role": "user", "content": "Explain the concept of quantum entanglement."},
+# ]
+# text = tokenizer.apply_chat_template(
+#     messages,
+#     tokenize=False,
+#     add_generation_prompt=True
+# )
+# inputs = tokenizer(text, return_tensors="pt").to(model.device)
+# output_ids = model.generate(**inputs, max_new_tokens=100, temperature=0.7)
+# output_text = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+# print(output_text)
+```
 
 ## 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. -->
+LoRI models were extensively evaluated across various domains and tasks. For the "LoRI-S_nlu_llama3_rank_32" adapter, it was fine-tuned for Natural Language Understanding (NLU) tasks. Other LoRI adapters in the collection were trained for:
+-   **Code Generation:** Using datasets like CodeAlpaca.
+-   **Mathematical Reasoning:** Using datasets like GSM8K.
+-   **Safety Alignment:** Using datasets like Saferpaca.
 
-[More Information Needed]
+Further details on specific datasets used for NLU tasks can be found in the [original paper](https://arxiv.org/abs/2504.07448) and the [LoRI GitHub repository](https://github.com/juzhengz/LoRI/).
 
 ### 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]
-
+LoRI training involves a two-stage process implemented using Fully Sharded Data Parallel (FSDP) for multi-GPU environments:
+1.  **LoRI-D (Density/Distribution) training:** Initial training where the projection matrices `A` are frozen as random projections.
+2.  **LoRI-S (Sparsification) training:** Continues training from the `LoRI-D` stage, where matrix `B` is sparsified using task-specific masks, typically at 90% sparsity.
 
 #### 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]
+-   **Base Models:** LLaMA-3-8B and Mistral-7B were used across experiments.
+-   **Adapter Ranks (`r`):** 32 (for this model) and 64.
+-   **LoRA Alpha (`lora_alpha`):** 64 (from `adapter_config.json`).
+-   **LoRA Dropout (`lora_dropout`):** 0.05 (from `adapter_config.json`).
+-   **Sparsity:** Typically 90% for LoRI-S adapters.
+-   **Training regime:** Mixed precision (e.g., `bf16`).
 
 ## 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]
+LoRI was evaluated across natural language understanding, mathematical reasoning, code generation (e.g., HumanEval), and safety alignment tasks. The paper presents comprehensive results comparing LoRI against full fine-tuning and other PEFT methods.
 
 ### Results
 
-[More Information Needed]
-
-#### Summary
-
-
+Extensive experiments demonstrate that LoRI outperforms full fine-tuning and existing PEFT methods, while using up to 95% fewer trainable parameters than standard LoRA. In multi-task experiments, LoRI enables effective adapter merging and continual learning with reduced cross-task interference. For detailed quantitative results, please refer to the [official paper](https://huggingface.co/papers/2504.07448).
 
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
 
-[More Information Needed]
+LoRI modifies the standard LoRA architecture. The `A` matrices are frozen as random projections, and the `B` matrices are sparsified using task-specific masks. This design aims to promote monosemanticity (where adapters specialize in specific knowledge) and reduce interference between different adapters, especially in multi-task and continual learning settings. The objective remains to efficiently fine-tune the LLM for various downstream tasks.
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
+The training scripts are designed to leverage multi-GPU setups using PyTorch's Fully Sharded Data Parallel (FSDP) for efficient distributed training.
 
 #### Software
 
-[More Information Needed]
+-   Python 3.10
+-   PyTorch
+-   Transformers library
+-   PEFT library (version `0.12.0`)
 
-## Citation [optional]
+## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+If you use LoRI in your work, please cite:
 
-**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]
+```bibtex
+@article{zhang2025lori,
+  title={LoRI: Reducing Cross-Task Interference in Multi-Task Low-Rank Adaptation},
+  author={Zhang, Juzheng and You, Jiacheng and Panda, Ashwinee and Goldstein, Tom},
+  journal={arXiv preprint arXiv:2504.07448},
+  year={2025}
+}
+```
 
 ## Model Card Contact
 
-[More Information Needed]
+For questions, feel free to reach out via the [LoRI GitHub repository](https://github.com/juzhengz/LoRI/) or contact the authors of the paper.
+
 ### Framework versions
 
-- PEFT 0.12.0
+-   PEFT 0.12.0