MoE-LLaVA Model
Collection
9 items
โข
Updated
โข
9
MoE-LLaVA shows excellent performance in multi-modal learning.
Highly recommend trying out our web demo by the following command, which incorporates all features currently supported by MoE-LLaVA. We also provide online demo in Huggingface Spaces.
# use phi2
deepspeed --include localhost:0 moellava/serve/gradio_web_server.py --model-path "LanguageBind/MoE-LLaVA-Phi2-2.7B-4e"
# use qwen
deepspeed --include localhost:0 moellava/serve/gradio_web_server.py --model-path "LanguageBind/MoE-LLaVA-Qwen-1.8B-4e"
# use stablelm
deepspeed --include localhost:0 moellava/serve/gradio_web_server.py --model-path "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e"
# use phi2
deepspeed --include localhost:0 moellava/serve/cli.py --model-path "LanguageBind/MoE-LLaVA-Phi2-2.7B-4e" --image-file "image.jpg"
# use qwen
deepspeed --include localhost:0 moellava/serve/cli.py --model-path "LanguageBind/MoE-LLaVA-Qwen-1.8B-4e" --image-file "image.jpg"
# use stablelm
deepspeed --include localhost:0 moellava/serve/cli.py --model-path "LanguageBind/MoE-LLaVA-StableLM-1.6B-4e" --image-file "image.jpg"
Model | LLM | Checkpoint | Avg | VQAv2 | GQA | VizWiz | SQA | T-VQA | POPE | MM-Bench | LLaVA-Bench-Wild | MM-Vet |
---|---|---|---|---|---|---|---|---|---|---|---|---|
MoE-LLaVA-1.6Bร4-Top2 | 1.6B | LanguageBind/MoE-LLaVA-StableLM-1.6B-4e | 60.0 | 76.0 | 60.4 | 37.2 | 62.6 | 47.8 | 84.3 | 59.4 | 85.9 | 26.1 |
MoE-LLaVA-1.8Bร4-Top2 | 1.8B | LanguageBind/MoE-LLaVA-Qwen-1.8B-4e | 60.2 | 76.2 | 61.5 | 32.6 | 63.1 | 48.0 | 87.0 | 59.6 | 88.7 | 25.3 |
MoE-LLaVA-2.7Bร4-Top2 | 2.7B | LanguageBind/MoE-LLaVA-Phi2-2.7B-4e | 63.9 | 77.1 | 61.1 | 43.4 | 68.7 | 50.2 | 85.0 | 65.5 | 93.2 | 31.1 |
git clone https://github.com/PKU-YuanGroup/MoE-LLaVA
cd MoE-LLaVA
conda create -n moellava python=3.10 -y
conda activate moellava
pip install --upgrade pip # enable PEP 660 support
pip install -e .
pip install -e ".[train]"
pip install flash-attn --no-build-isolation
# Below are optional. For Qwen model.
git clone https://github.com/Dao-AILab/flash-attention
cd flash-attention && pip install .
# Below are optional. Installing them might be slow.
# pip install csrc/layer_norm
# If the version of flash-attn is higher than 2.1.1, the following is not needed.
# pip install csrc/rotary
The training & validating instruction is in TRAIN.md & EVAL.md.
The instruction is in CUSTOM.md.
The instruction is in VISUALIZATION.md.
We open source all codes. If you want to load the model (e.g. LanguageBind/MoE-LLaVA
) on local, you can use the following code snippets.
Using the following command to run the code.
deepspeed predict.py
import torch
from moellava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN
from moellava.conversation import conv_templates, SeparatorStyle
from moellava.model.builder import load_pretrained_model
from moellava.utils import disable_torch_init
from moellava.mm_utils import tokenizer_image_token, get_model_name_from_path, KeywordsStoppingCriteria
def main():
disable_torch_init()
image = 'moellava/serve/examples/extreme_ironing.jpg'
inp = 'What is unusual about this image?'
model_path = 'LanguageBind/MoE-LLaVA-Phi2-2.7B-4e' # LanguageBind/MoE-LLaVA-Qwen-1.8B-4e or LanguageBind/MoE-LLaVA-StableLM-1.6B-4e
device = 'cuda'
load_4bit, load_8bit = False, False # FIXME: Deepspeed support 4bit or 8bit?
model_name = get_model_name_from_path(model_path)
tokenizer, model, processor, context_len = load_pretrained_model(model_path, None, model_name, load_8bit, load_4bit, device=device)
image_processor = processor['image']
conv_mode = "phi" # qwen or stablelm
conv = conv_templates[conv_mode].copy()
roles = conv.roles
image_tensor = image_processor.preprocess(image, return_tensors='pt')['pixel_values'].to(model.device, dtype=torch.float16)
print(f"{roles[1]}: {inp}")
inp = DEFAULT_IMAGE_TOKEN + '\n' + inp
conv.append_message(conv.roles[0], inp)
conv.append_message(conv.roles[1], None)
prompt = conv.get_prompt()
input_ids = tokenizer_image_token(prompt, tokenizer, IMAGE_TOKEN_INDEX, return_tensors='pt').unsqueeze(0).cuda()
stop_str = conv.sep if conv.sep_style != SeparatorStyle.TWO else conv.sep2
keywords = [stop_str]
stopping_criteria = KeywordsStoppingCriteria(keywords, tokenizer, input_ids)
with torch.inference_mode():
output_ids = model.generate(
input_ids,
images=image_tensor,
do_sample=True,
temperature=0.2,
max_new_tokens=1024,
use_cache=True,
stopping_criteria=[stopping_criteria])
outputs = tokenizer.decode(output_ids[0, input_ids.shape[1]:], skip_special_tokens=True).strip()
print(outputs)
if __name__ == '__main__':
main()
If you find our paper and code useful in your research, please consider giving a star :star: and citation :pencil:.
@misc{lin2024moellava,
title={MoE-LLaVA: Mixture of Experts for Large Vision-Language Models},
author={Bin Lin and Zhenyu Tang and Yang Ye and Jiaxi Cui and Bin Zhu and Peng Jin and Junwu Zhang and Munan Ning and Li Yuan},
year={2024},
eprint={2401.15947},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
@article{lin2023video,
title={Video-LLaVA: Learning United Visual Representation by Alignment Before Projection},
author={Lin, Bin and Zhu, Bin and Ye, Yang and Ning, Munan and Jin, Peng and Yuan, Li},
journal={arXiv preprint arXiv:2311.10122},
year={2023}
}