|
--- |
|
license: apache-2.0 |
|
language: |
|
- en |
|
base_model: |
|
- Qwen/Qwen2-VL-2B-Instruct |
|
tags: |
|
- food |
|
- recipe |
|
--- |
|
# Adapting Multimodal Large Language Models to Domains via Post-Training |
|
|
|
This repos contains the **food MLLM developed from Qwen-2-VL-2B-Instruct** in our paper: [On Domain-Specific Post-Training for Multimodal Large Language Models](https://huggingface.co/papers/2411.19930). |
|
|
|
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='left'> |
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/650801ced5578ef7e20b33d4/bRu85CWwP9129bSCRzos2.png" width="1000"> |
|
</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 |
|
|
|
Our model architecture aligns with the base model: Qwen-2-VL-Instruct. We provide a usage example below, and you may refer to the official [Qwen-2-VL-Instruct repository](https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct) for more advanced usage instructions. |
|
|
|
**Note:** For AdaMLLM, always place the image at the beginning of the input instruction in the messages. |
|
|
|
<details> |
|
<summary> Click to expand </summary> |
|
|
|
1. Set up |
|
```bash |
|
pip install qwen-vl-utils |
|
``` |
|
2. Inference |
|
```python |
|
from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor |
|
from qwen_vl_utils import process_vision_info |
|
|
|
# default: Load the model on the available device(s) |
|
model = Qwen2VLForConditionalGeneration.from_pretrained( |
|
"AdaptLLM/food-Qwen2-VL-2B-Instruct", torch_dtype="auto", device_map="auto" |
|
) |
|
|
|
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios. |
|
# model = Qwen2VLForConditionalGeneration.from_pretrained( |
|
# "AdaptLLM/food-Qwen2-VL-2B-Instruct", |
|
# torch_dtype=torch.bfloat16, |
|
# attn_implementation="flash_attention_2", |
|
# device_map="auto", |
|
# ) |
|
|
|
# default processer |
|
processor = AutoProcessor.from_pretrained("AdaptLLM/food-Qwen2-VL-2B-Instruct") |
|
|
|
# The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage. |
|
# min_pixels = 256*28*28 |
|
# max_pixels = 1280*28*28 |
|
# processor = AutoProcessor.from_pretrained("AdaptLLM/food-Qwen2-VL-2B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels) |
|
|
|
# NOTE: For AdaMLLM, always place the image at the beginning of the input instruction in the messages. |
|
messages = [ |
|
{ |
|
"role": "user", |
|
"content": [ |
|
{ |
|
"type": "image", |
|
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", |
|
}, |
|
{"type": "text", "text": "Describe this image."}, |
|
], |
|
} |
|
] |
|
|
|
# Preparation for inference |
|
text = processor.apply_chat_template( |
|
messages, tokenize=False, add_generation_prompt=True |
|
) |
|
image_inputs, video_inputs = process_vision_info(messages) |
|
inputs = processor( |
|
text=[text], |
|
images=image_inputs, |
|
videos=video_inputs, |
|
padding=True, |
|
return_tensors="pt", |
|
) |
|
inputs = inputs.to("cuda") |
|
|
|
# Inference: Generation of the output |
|
generated_ids = model.generate(**inputs, max_new_tokens=128) |
|
generated_ids_trimmed = [ |
|
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) |
|
] |
|
output_text = processor.batch_decode( |
|
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False |
|
) |
|
print(output_text) |
|
``` |
|
|
|
</details> |
|
|
|
## 2. To Evaluate Any MLLM on Domain-Specific Benchmarks |
|
|
|
Refer to the [food-VQA-benchmark](https://huggingface.co/datasets/AdaptLLM/food-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} |
|
} |
|
``` |
|
|
