Haoran Wei*, Lingyu Kong*, Jinyue Chen, Liang Zhao, Zheng Ge, Jinrong Yang, Jianjian Sun, Chunrui Han, Xiangyu Zhang
- [2024/3/16]๐ฅ๐ฅ๐ฅI found many friends very interested in Vary-tiny(OPT-125M), so I opened source it here, a PDF-dense OCR and object detection version.
- [2023/1/23]๐ฅ๐ฅ๐ฅWe release the Vary-toy here. Besides, we show the super good Vary-family results here.
- [2023/12/29]๐ฅ๐ฅ๐ฅWe will release a new model (a small-size Vary, about 2B) at the beginning of next month and introduce a new feature (object detection). Our online demo will be temporarily closed to prepare for the deployment of the new model.
- [2023/12/11] We released the online demo, have fun!
- [2023/12/11] We released the codes of Vary (train and inference)!
- Clone this repository and navigate to the Vary folder
git clone https://github.com/Ucas-HaoranWei/Vary.git
cd Vary- Install Package
conda create -n vary python=3.10 -y
conda activate vary
pip install e .- Install Flash-Attention
pip install ninja
pip install flash-attn --no-build-isolation
- If you are in urgent need of weights for your research recently, please contact me by email.
- Download the CLIP-VIT-L in Hugging Face
-
Update the CLIP-VIT path in the codes (/cache/vit-large-patch14/) to your path.
python vary/demo/run_qwen_vary.py --model-name /vary/model/path/ --image-file /an/image/file.png- We currently do not plan to open source the weights of the intermediate.
- However, we release the train codes. So you can train on your own dataset. If you want to do this, you can try this:
- For Vary-base (one machine, if you have multiple machines you need to prepare your host file)
deepspeed Vary/train/train_qwen_vary.py --deepspeed /Vary/zero_config/zero2.json
--model_name_or_path /Qwen-7B/path/
--vision_tower /vit-large-patch14/path/
--freeze_vision_tower True
--freeze_lm_model False
--vision_select_layer -2
--use_im_start_end True
--bf16 True
--per_device_eval_batch_size 4
--gradient_accumulation_steps 1
--evaluation_strategy "no"
--save_strategy "steps"
--save_steps 5000
--save_total_limit 1
--weight_decay 0.
--warmup_ratio 0.03
--lr_scheduler_type "cosine"
--logging_steps 1 --tf32 True
--model_max_length 4096
--gradient_checkpointing True
--dataloader_num_workers 4
--report_to none
--per_device_train_batch_size 4
--num_train_epochs 1
--learning_rate 5e-5
--datasets data_name1+data_name2+data_name3
--output_dir /path/to/output/- For Vary-tiny
deepspeed Vary/train/train_opt.py --deepspeed /Vary/zero_config/zero2.json
--model_name_or_path /opt125m/path/
--conversation_version opt
--freeze_vision_tower False
--freeze_lm_model False
--use_im_start_end True
--bf16 True
--per_device_eval_batch_size 4
--gradient_accumulation_steps 1
--evaluation_strategy "no"
--save_strategy "steps"
--save_steps 5000
--save_total_limit 1
--weight_decay 0.
--warmup_ratio 0.03
--lr_scheduler_type "cosine"
--logging_steps 1 --tf32 True
--model_max_length 4096
--gradient_checkpointing True
--dataloader_num_workers 4
--report_to none
--per_device_train_batch_size 16
--num_train_epochs 1
--learning_rate 5e-5
--datasets data_name1+data_name2+data_name3
--output_dir /path/to/output/If you have any questions related to the code or the paper, feel free to email ([email protected]).
- LLaVA: the codebase we built upon!
- Qwen: the LLM base model of Vary, which is good at both English and Chinese!
If you find our work useful in your research, please consider citing Vary:
@article{wei2023vary,
title={Vary: Scaling up the Vision Vocabulary for Large Vision-Language Models},
author={Wei, Haoran and Kong, Lingyu and Chen, Jinyue and Zhao, Liang and Ge, Zheng and Yang, Jinrong and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
journal={arXiv preprint arXiv:2312.06109},
year={2023}
}
@article{wei2024small,
title={Small Language Model Meets with Reinforced Vision Vocabulary},
author={Wei, Haoran and Kong, Lingyu and Chen, Jinyue and Zhao, Liang and Ge, Zheng and Yu, En and Sun, Jianjian and Han, Chunrui and Zhang, Xiangyu},
journal={arXiv preprint arXiv:2401.12503},
year={2024}
}