--- license: llama3.1 datasets: - yale-nlp/MDCure-72k language: - en base_model: - meta-llama/Meta-Llama-3.1-8B-Instruct tags: - multi-document - long-context - Long Context --- # MDCure-LLAMA3.1-8B-Instruct [📄 Paper](https://arxiv.org/pdf/2410.23463) | [🤗 HF Collection](https://huggingface.co./collections/yale-nlp/mdcure-6724914875e87f41e5445395) | [⚙️ GitHub Repo](https://github.com/yale-nlp/MDCure) ## Introduction **MDCure** is an effective and scalable procedure for generating high-quality multi-document (MD) instruction tuning data to improve MD capabilities of LLMs. Using MDCure, we construct a suite of MD instruction datasets complementary to collections such as [FLAN](https://github.com/google-research/FLAN) and fine-tune a variety of already instruction-tuned LLMs from the FlanT5, Qwen2, and LLAMA3.1 model families, up to 70B parameters in size. We additionally introduce **MDCureRM**, an evaluator model specifically designed for the MD setting to filter and select high-quality MD instruction data in a cost-effective, RM-as-a-judge fashion. Extensive evaluations on a wide range of MD and long-context benchmarks spanning various tasks show MDCure consistently improves performance over pre-trained baselines and over corresponding base models by up to 75.5%. We release MDCure datasets of size 12k, 36k, and 72k. We also release MDCureRM and the best MDCure'd model for each architecture/size combination. To access all our models and datasets, please visit our [HF Collection](https://huggingface.co./collections/yale-nlp/mdcure-6724914875e87f41e5445395). For further details regarding dataset construction, please see our [paper](https://arxiv.org/pdf/2410.23463) and [Github repo](https://github.com/yale-nlp/MDCure). For additional details regarding how to use **yale-nlp/MDCure-LLAMA3.1-8B-Instruct**, please see below.

The MDCure pipeline generates diverse multi-document instructions, filters them via fine-grained scoring by MDCureRM, and tunes a base LLM to enhance its multi-document capabilities.

## Model Details **yale-nlp/MDCure-LLAMA3.1-8B-Instruct** is initialized from [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co./meta-llama/Meta-Llama-3.1-8B-Instruct) and fine-tuned on the [MDCure-72k](https://huggingface.co./datasets/yale-nlp/MDCure-72k) dataset. ## Requirements We recommend using the latest version of HF Transformers, or any `transformers>=4.45.0`, to avoid any potential errors when using this model. ## Quickstart Below we provide a code snippet demonstrating how to load the tokenizer and model and generate content in response to an input context concerning multiple source documents and a related question or instruction. We strongly recommend to separate the texts and/or instruction using `\n\n` or `` to maintain consistency with the format of the data used during training. ```python model = AutoModelForCausalLM.from_pretrained("yale-nlp/MDCure-LLAMA3.1-8B-Instruct", device_map='auto',torch_dtype="auto") tokenizer = AutoTokenizer.from_pretrained("yale-nlp/MDCure-LLAMA3.1-8B-Instruct") source_text_1 = ... source_text_2 = ... source_text_3 = ... prompt = f"{source_text_1}\n\n{source_text_2}\n\n{source_text_3}\n\nWhat happened in CHAMPAIGN regarding Lovie Smith and the 2019 defense improvements? Respond with 1-2 sentences." messages = [ {"role": "system", "content": "You are an assistant with strong multi-document processing skills."}, {"role": "user", "content": prompt}, ] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) model_inputs = tokenizer([text], return_tensors="pt", return_token_type_ids=False).to(model.device) generated_ids = model.generate(**model_inputs, max_new_tokens=512) generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)] response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0] print(response) ``` You can also run conversational inference with the model using the Transformers `pipeline` abstraction, described further in the official LLAMA3.1-8B-Instruct [model card](https://huggingface.co./meta-llama/Llama-3.1-8B-Instruct). ## All MDCure Models We open-source our custom multi-document instruction scoring model, MDCureRM, as well as our best MDCure'd models at the following links: | Model | Huggingface Repo | Description | |---------------------------|---------------------|------------------------------| | **MDCureRM** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCureRM) | Multi-objective reward model to score and filter MD instruction data more cheaply and effectively than GPT-3.5-Turbo | | **MDCure-FlanT5-Base** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-FlanT5-Base) | **FlanT5-Base** fine-tuned with MDCure-72k | | **MDCure-FlanT5-Large** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-FlanT5-Large) | **FlanT5-Large** fine-tuned with MDCure-72k | | **MDCure-Qwen2-1.5B-Instruct** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-Qwen2-1.5B-Instruct) | **Qwen2-1.5B-Instruct** fine-tuned with MDCure-72k | | **MDCure-Qwen2-7B-Instruct** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-Qwen2-7B-Instruct) | **Qwen2-7B-Instruct** fine-tuned with MDCure-72k | | **MDCure-LLAMA3.1-8B-Instruct** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-LLAMA3.1-8B-Instruct) | **LLAMA3.1-8B-Instruct** fine-tuned with MDCure-72k | | **MDCure-LLAMA3.1-70B-Instruct** | [🤗 HF Repo](https://huggingface.co./yale-nlp/MDCure-LLAMA3.1-70B-Instruct) | **LLAMA3.1-70B-Instruct** fine-tuned with MDCure-72 | ## Citation If you find our work useful, please cite our paper as: ```bibtex @article{liu2024mdcure, title={MDCure: A Scalable Pipeline for Multi-Document Instruction-Following}, author={Gabrielle Kaili-May Liu and Bowen Shi and Avi Caciularu and Idan Szpektor and Arman Cohan}, journal={arXiv preprint arXiv:2410.23463}, year={2024}, url={https://arxiv.org/abs/2410.23463} } ```