Instructions to use LanguageBind/Video-LLaVA-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LanguageBind/Video-LLaVA-7B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LanguageBind/Video-LLaVA-7B")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("LanguageBind/Video-LLaVA-7B")
model = AutoModelForCausalLM.from_pretrained("LanguageBind/Video-LLaVA-7B")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LanguageBind/Video-LLaVA-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LanguageBind/Video-LLaVA-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LanguageBind/Video-LLaVA-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LanguageBind/Video-LLaVA-7B

SGLang

How to use LanguageBind/Video-LLaVA-7B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LanguageBind/Video-LLaVA-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LanguageBind/Video-LLaVA-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LanguageBind/Video-LLaVA-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LanguageBind/Video-LLaVA-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LanguageBind/Video-LLaVA-7B with Docker Model Runner:
```
docker model run hf.co/LanguageBind/Video-LLaVA-7B
```

新权重无法使用 AttributeError: 'LlavaConfig' object has no attribute 'X'

#10

by Hugging-xinl - opened May 10, 2024

Discussion

Hugging-xinl

May 10, 2024

Traceback (most recent call last):
File "/home/ubuntu/Indentify/autodl/autodl-tmp/Video-LLaVA-7B/Video_llava.py", line 274, in
Audio_modellist = init(args.LLaVA_model_path)
File "/home/ubuntu/Indentify/autodl/autodl-tmp/Video-LLaVA-7B/Video_llava.py", line 56, in init
Audio_modellist = load_pretrained_model(
File "/home/ubuntu/Indentify/autodl/autodl-tmp/Video-LLaVA-7B/Video-LLaVA/llava/model/builder.py", line 142, in load_pretrained_model
X = model.config.X
File "/home/ubuntu/.conda/envs/video/lib/python3.10/site-packages/transformers/configuration_utils.py", line 261, in getattribute
return super().getattribute(key)
AttributeError: 'LlavaConfig' object has no attribute 'X'

之前的权重加载后没有问题，但更新model-0000x-of-00002.safetensor后无法使用，是我版本出现了问题，还是下载的权重有问题

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment