|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- AdaptLLM/biomed-visual-instructions |
|
language: |
|
- en |
|
base_model: |
|
- Lin-Chen/open-llava-next-llama3-8b |
|
tags: |
|
- medical |
|
- biology |
|
--- |
|
# Adapting Multimodal Large Language Models to Domains via Post-Training |
|
|
|
This repo contains the **biomedicine MLLM developed from LLaVA-NeXT-Llama3-8B** in our paper: [On Domain-Specific Post-Training for Multimodal Large Language Models](https://huggingface.co/papers/2411.19930). The correspoding training dataset is in [medicine-visual-instructions](https://huggingface.co/datasets/AdaptLLM/medicine-visual-instructions). |
|
|
|
The main project page is: [Adapt-MLLM-to-Domains](https://huggingface.co/AdaptLLM/Adapt-MLLM-to-Domains/edit/main/README.md) |
|
|
|
We investigate domain adaptation of MLLMs through post-training, focusing on data synthesis, training pipelines, and task evaluation. |
|
**(1) Data Synthesis**: Using open-source models, we develop a visual instruction synthesizer that effectively generates diverse visual instruction tasks from domain-specific image-caption pairs. **Our synthetic tasks surpass those generated by manual rules, GPT-4, and GPT-4V in enhancing the domain-specific performance of MLLMs.** |
|
**(2) Training Pipeline**: While the two-stage training--initially on image-caption pairs followed by visual instruction tasks--is commonly adopted for developing general MLLMs, we apply a single-stage training pipeline to enhance task diversity for domain-specific post-training. |
|
**(3) Task Evaluation**: We conduct experiments in two domains, biomedicine and food, by post-training MLLMs of different sources and scales (e.g., Qwen2-VL-2B, LLaVA-v1.6-8B, Llama-3.2-11B), and then evaluating MLLM performance on various domain-specific tasks. |
|
|
|
<p align='center'> |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/-Jp7pAsCR2Tj4WwfwsbCo.png" width="600"> |
|
</p> |
|
|
|
## Resources |
|
**🤗 We share our data and models with example usages, feel free to open any issues or discussions! 🤗** |
|
|
|
| Model | Repo ID in HF 🤗 | Domain | Base Model | Training Data | Evaluation Benchmark | |
|
|:----------------------------------------------------------------------------|:--------------------------------------------|:--------------|:-------------------------|:------------------------------------------------------------------------------------------------|-----------------------| |
|
| [Visual Instruction Synthesizer](https://huggingface.co/AdaptLLM/visual-instruction-synthesizer) | AdaptLLM/visual-instruction-synthesizer | - | open-llava-next-llama3-8b | VisionFLAN and ALLaVA | - | |
|
| [AdaMLLM-med-2B](https://huggingface.co/AdaptLLM/biomed-Qwen2-VL-2B-Instruct) | AdaptLLM/biomed-Qwen2-VL-2B-Instruct | Biomedicine | Qwen2-VL-2B-Instruct | [biomed-visual-instructions](https://huggingface.co/datasets/AdaptLLM/biomed-visual-instructions) | [biomed-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/biomed-VQA-benchmark) | |
|
| [AdaMLLM-food-2B](https://huggingface.co/AdaptLLM/food-Qwen2-VL-2B-Instruct) | AdaptLLM/food-Qwen2-VL-2B-Instruct | Food | Qwen2-VL-2B-Instruct | [food-visual-instructions](https://huggingface.co/datasets/AdaptLLM/food-visual-instructions) | [food-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/food-VQA-benchmark) | |
|
| [AdaMLLM-med-8B](https://huggingface.co/AdaptLLM/biomed-LLaVA-NeXT-Llama3-8B) | AdaptLLM/biomed-LLaVA-NeXT-Llama3-8B | Biomedicine | open-llava-next-llama3-8b | [biomed-visual-instructions](https://huggingface.co/datasets/AdaptLLM/biomed-visual-instructions) | [biomed-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/biomed-VQA-benchmark) | |
|
| [AdaMLLM-food-8B](https://huggingface.co/AdaptLLM/food-LLaVA-NeXT-Llama3-8B) |AdaptLLM/food-LLaVA-NeXT-Llama3-8B | Food | open-llava-next-llama3-8b | [food-visual-instructions](https://huggingface.co/datasets/AdaptLLM/food-visual-instructions) | [food-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/food-VQA-benchmark) | |
|
| [AdaMLLM-med-11B](https://huggingface.co/AdaptLLM/biomed-Llama-3.2-11B-Vision-Instruct) | AdaptLLM/biomed-Llama-3.2-11B-Vision-Instruct | Biomedicine | Llama-3.2-11B-Vision-Instruct | [biomed-visual-instructions](https://huggingface.co/datasets/AdaptLLM/biomed-visual-instructions) | [biomed-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/biomed-VQA-benchmark) | |
|
| [AdaMLLM-food-11B](https://huggingface.co/AdaptLLM/food-Llama-3.2-11B-Vision-Instruct) | AdaptLLM/food-Llama-3.2-11B-Vision-Instruct | Food | Llama-3.2-11B-Vision-Instruct | [food-visual-instructions](https://huggingface.co/datasets/AdaptLLM/food-visual-instructions) | [food-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/food-VQA-benchmark) | |
|
|
|
**Code**: [https://github.com/bigai-ai/QA-Synthesizer](https://github.com/bigai-ai/QA-Synthesizer) |
|
|
|
## 1. To Chat with AdaMLLM |
|
|
|
```python |
|
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration |
|
import torch |
|
from PIL import Image |
|
import requests |
|
|
|
# Define your input image and instruction here: |
|
## image |
|
url = "https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/bRu85CWwP9129bSCRzos2.png" |
|
image = Image.open(requests.get(url, stream=True).raw).convert("RGB") |
|
|
|
instruction = "What's in the image?" |
|
|
|
model_path='AdaptLLM/biomed-LLaVA-NeXT-Llama3-8B' |
|
|
|
# =========================== Do NOT need to modify the following =============================== |
|
# Load the processor |
|
processor = LlavaNextProcessor.from_pretrained(model_path) |
|
|
|
# Define image token |
|
image_token = "<|reserved_special_token_4|>" |
|
|
|
# Format the prompt |
|
prompt = ( |
|
f"<|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\n" |
|
f"You are a helpful language and vision assistant. You are able to understand the visual content that the user provides, and assist the user with a variety of tasks using natural language." |
|
f"<|eot_id|><|start_header_id|>user<|end_header_id|>\n\n" |
|
f"{image_token}\n{instruction}<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" |
|
) |
|
|
|
# Load the model |
|
model = LlavaNextForConditionalGeneration.from_pretrained(model_path, torch_dtype=torch.float16, device_map="auto") |
|
|
|
# Prepare inputs and generate output |
|
inputs = processor(images=image, text=prompt, return_tensors="pt").to(model.device) |
|
answer_start = int(inputs["input_ids"].shape[-1]) |
|
output = model.generate(**inputs, max_new_tokens=512) |
|
|
|
# Decode predictions |
|
pred = processor.decode(output[0][answer_start:], skip_special_tokens=True) |
|
print(pred) |
|
``` |
|
|
|
## 2. To Evaluate Any MLLM on Domain-Specific Benchmarks |
|
|
|
Refer to the [biomed-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/biomed-VQA-benchmark) to reproduce our results and evaluate many other MLLMs on domain-specific benchmarks. |
|
|
|
## Citation |
|
If you find our work helpful, please cite us. |
|
|
|
[AdaMLLM](https://huggingface.co/papers/2411.19930) |
|
```bibtex |
|
@article{adamllm, |
|
title={On Domain-Specific Post-Training for Multimodal Large Language Models}, |
|
author={Cheng, Daixuan and Huang, Shaohan and Zhu, Ziyu and Zhang, Xintong and Zhao, Wayne Xin and Luan, Zhongzhi and Dai, Bo and Zhang, Zhenliang}, |
|
journal={arXiv preprint arXiv:2411.19930}, |
|
year={2024} |
|
} |
|
``` |
|
|
|
[Instruction Pre-Training](https://huggingface.co/papers/2406.14491) (EMNLP 2024) |
|
```bibtex |
|
@article{cheng2024instruction, |
|
title={Instruction Pre-Training: Language Models are Supervised Multitask Learners}, |
|
author={Cheng, Daixuan and Gu, Yuxian and Huang, Shaohan and Bi, Junyu and Huang, Minlie and Wei, Furu}, |
|
journal={arXiv preprint arXiv:2406.14491}, |
|
year={2024} |
|
} |
|
``` |
|
|
|
[Adapt LLM to Domains](https://huggingface.co/papers/2309.09530) (ICLR 2024) |
|
```bibtex |
|
@inproceedings{ |
|
cheng2024adapting, |
|
title={Adapting Large Language Models via Reading Comprehension}, |
|
author={Daixuan Cheng and Shaohan Huang and Furu Wei}, |
|
booktitle={The Twelfth International Conference on Learning Representations}, |
|
year={2024}, |
|
url={https://openreview.net/forum?id=y886UXPEZ0} |
|
} |
|
``` |
|
|
