[Project Page] [Paper] [HF Demo🤗] [Modelscope Demo🤖] [Model🤗] [Data]
- 2024.02.27 OneLLM is accepted by CVPR 2024!🎉
- 2023.12.01 Release model weights and inference code.
- Clone the repo into a local folder.
git clone https://github.com/csuhan/OneLLM
cd OneLLM- Install packages.
conda create -n onellm python=3.9 -y
conda activate onellm
pip install -r requirements.txt
# install pointnet
cd model/lib/pointnet2
python setup.py install- Install Apex. (Optional)
git clone https://github.com/NVIDIA/apex
cd apex
pip install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./We provide a preview model on the Hugging Face at: csuhan/OneLLM-7B.
Huggingface Demo: csuhan/OneLLM.
Local Demo: Assume you have downloaded the weights to ${WEIGHTS_DIR}. Then run the following command to start a gradio demo locally.
python demos/multi_turn_mm.py --gpu_ids 0 --tokenizer_path config/llama2/tokenizer.model --llama_config config/llama2/7B.json --pretrained_path ${WEIGHTS_DIR}/consolidated.00-of-01.pthCLI Demo:
python demos/cli.py --image_path ${IMAGE_PATH} --gpu_ids 0 --tokenizer_path config/llama2/tokenizer.model --llama_config config/llama2/7B.json --pretrained_path ${WEIGHTS_DIR}/consolidated.00-of-01.pthPlease check Data.md for more detail.
Please check Evaluation.md for more detail.
Single Node 8-GPU Training: exps/image_text_pretrain_8gpu.sh
Show More
torchrun --nproc_per_node=8 main_pretrain.py \
--epochs 1 --dataset image \
--batch_size 40 --accum_iter 16 \
--model_parallel_size 1 \
--data_parallel sdp \
--save_consolidated \
--llama_type onellm \
--llama_ckpt_dir ${LLAMA_7B_PATH} \
--llama_config config/llama2/7B.json \
--tokenizer_path config/llama2/tokenizer.model \
--auto_resume \
--weight_decay 0.1 --output_dir ${OUTPUT_DIR} \
--warmup_iters 2000 --lr_decay_iters 200000 --lr 5e-5 --min_lr 5e-6 --clip_grad 2 \
--save_freq 1000 \
2>&1 | tee -a ${OUTPUT_DIR}/output.logMulti Nodes DDP Training:
Run N scripts on N nodes at the time, then we can launch a multi-node DDP training. Following is an example script for one node:
MASTER_ADDR=IP_ADDRESS_OF_NODE_1
NNODES=N
MASTER_PORT=29500
NPROC_PER_NODE=8
RANK=0 or 1 or ... or N
bash
torchrun \
--nnodes=$NNODES \
--nproc_per_node=8 \
--node_rank=$RANK \
--master_port=$MASTER_PORT \
--master_addr=$MASTER_ADDR \
main_pretrain.py \
--epochs 1 --dataset image \
--batch_size 40 --accum_iter 16 \
--model_parallel_size 1 \
--data_parallel sdp \
--save_consolidated \
--llama_type onellm \
--llama_ckpt_dir ${LLAMA_7B_PATH} \
--llama_config config/llama2/7B.json \
--tokenizer_path config/llama2/tokenizer.model \
--auto_resume \
--weight_decay 0.1 --output_dir ${OUTPUT_DIR} \
--warmup_iters 2000 --lr_decay_iters 200000 --lr 5e-5 --min_lr 5e-6 --clip_grad 2 \
--save_freq 1000 \
2>&1 | tee -a ${OUTPUT_DIR}/output.log
Multi Node SLURM Training: exps/image_text_pretrain_slurm.sh
Show More
#!/bin/bash
#SBATCH --gres=gpu:8
#SBATCH -n 16
#SBATCH -N 2
#SBATCH --cpus-per-task=16
srun python -u main_pretrain.py \
--epochs 1 --dataset image \
--batch_size 40 --accum_iter 8 \
--model_parallel_size 1 \
--data_parallel sdp \
--save_consolidated \
--llama_type onellm \
--llama_ckpt_dir ${LLAMA_7B_PATH} \
--llama_config config/llama2/7B.json \
--tokenizer_path config/llama2/tokenizer.model \
--auto_resume \
--weight_decay 0.1 --output_dir ${OUTPUT_DIR} \
--warmup_iters 2000 --lr_decay_iters 200000 --lr 5e-5 --min_lr 5e-6 --clip_grad 2 \
--save_freq 1000 \
2>&1 | tee -a ${OUTPUT_DIR}/output.logStage II Pretraining: Assume we have the pretrained ${IMAGE_TEXT_MODEL}, run exps/multimodal_text_pretrain_stage2.sh for video-audio-point-text pretraining.
Stage III Pretraining: Assume we have the pretrained ${STAGE2_MODEL}, run exps/multimodal_text_pretrain_stage3.sh for depth-normal-imu-fmri-text pretraining.
Assume we have the pretrained ${STAGE3_MODEL}, run exps/multimodal_text_finetune.sh for multimodal instruction tuning.
@InProceedings{han2023onellm,
title={OneLLM: One Framework to Align All Modalities with Language},
author={Han, Jiaming and Gong, Kaixiong and Zhang, Yiyuan and Wang, Jiaqi and Zhang, Kaipeng and Lin, Dahua and Qiao, Yu and Gao, Peng and Yue, Xiangyu},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2024}
}
LLaMA, LLaMA-Adapter, LLaMA2-Accessory, Meta-Transformer, ChatBridge
This project is developed based on Llama 2, please refer to the LLAMA 2 Community License.