|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- yale-nlp/MDCure-72k |
|
language: |
|
- en |
|
base_model: |
|
- google/flan-t5-base |
|
tags: |
|
- multi-document |
|
- long-context |
|
- Long Context |
|
--- |
|
|
|
# MDCure-FlanT5-Large |
|
|
|
|
|
[📄 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-FlanT5-Large**, please see below. |
|
|
|
<p align="center"> |
|
<img src="fig1.png" width="90%"> |
|
</p> |
|
<p align="center" style="margin-top: 0; padding-top: 0;"> |
|
<em>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.</em> |
|
</p> |
|
|
|
## Model Details |
|
|
|
**yale-nlp/MDCure-FlanT5-Large** is initialized from [google/flan-t5-large](https://huggingface.co/google/flan-t5-large) 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>4.35.0`, to avoid any potential versioning 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 `<doc-sep>` to maintain consistency with the format of the data used during training. |
|
|
|
```python |
|
model = AutoModelForSeq2SeqLM.from_pretrained("yale-nlp/MDCure-FlanT5-Large", device_map='auto',torch_dtype="auto",) |
|
tokenizer = AutoTokenizer.from_pretrained("yale-nlp/MDCure-FlanT5-Large") |
|
|
|
source_text_1 = ... |
|
source_text_2 = ... |
|
source_text_3 = ... |
|
input_text = 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." |
|
|
|
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to(model.device) |
|
outputs = model.generate(input_ids) |
|
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
``` |
|
|
|
## 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} |
|
} |
|
``` |
