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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use LanguageBind/Video-LLaVA-7B-hf 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-hf"
# 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-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

How to use LanguageBind/Video-LLaVA-7B-hf 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-hf" \
    --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-hf",
		"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-hf" \
        --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-hf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

Unable to import VideoLlavaProcessor and VideoLlavaForConditionalGeneration

by Rex-Shih - opened May 12, 2024

Discussion

Rex-Shih

May 12, 2024

Is this issue related to the transformers package? I am unable to import VideoLlavaProcessor and VideoLlavaForConditionalGeneration in the latest version of transformers(4.40.2).

Bilgames

May 16, 2024

Same issue here

LanguageBind

Owner May 16, 2024

upgrade transformers

pip install -U transformers

LanguageBind changed discussion status to closed May 17, 2024

taniarini

May 17, 2024

This did not work for me. I get the same error. I have transformers version 4.40.2.

LanguageBind

Owner May 21, 2024

This did not work for me. I get the same error. I have transformers version 4.40.2.

Try again. Thanks!

Bilgames

May 22, 2024

@LanguageBind Ultimately that worked for me, thanks!

n3xt1lxs

Jan 6, 2025

@LanguageBind hello dev , i cant Unable to import VideoLlavaProcessor but my VideoLlavaForConditionalGeneration i can use , i use tokenizers-0.21.0 transformers-4.47.1 and already pip install -U transformers in 09:47 06/01/68

how to fix it?

n3xt1lxs

Jan 6, 2025

@LanguageBind hello dev , i cant Unable to import VideoLlavaProcessor but my VideoLlavaForConditionalGeneration i can use , i use tokenizers-0.21.0 transformers-4.47.1 and already pip install -U transformers in 09:47 06/01/68

how to fix it?

i try pip install git+https://github.com/huggingface/transformers it can work , my VideoLlavaProcessor it already have , i try to run code but i got Loading checkpoint shards Killed , how to fix it?

shahiduljahid

Feb 3, 2025

Because of the updated transformer it's not working and didn't found any solution

shahiduljahid

Feb 4, 2025

@LanguageBind hello dev , i cant Unable to import VideoLlavaProcessor but my VideoLlavaForConditionalGeneration i can use , i use tokenizers-0.21.0 transformers-4.47.1 and already pip install -U transformers in 09:47 06/01/68

how to fix it?

i try pip install git+https://github.com/huggingface/transformers it can work , my VideoLlavaProcessor it already have , i try to run code but i got Loading checkpoint shards Killed , how to fix it?

i have same issue . i got Loading checkpoint shards Killed and kernel crashed

n3xt1lxs

Feb 7, 2025

@LanguageBind hello dev , i cant Unable to import VideoLlavaProcessor but my VideoLlavaForConditionalGeneration i can use , i use tokenizers-0.21.0 transformers-4.47.1 and already pip install -U transformers in 09:47 06/01/68

how to fix it?

i try pip install git+https://github.com/huggingface/transformers it can work , my VideoLlavaProcessor it already have , i try to run code but i got Loading checkpoint shards Killed , how to fix it?

i have same issue . i got Loading checkpoint shards Killed and kernel crashed

bro u can change to use llava video 7b qwen2 is so better and easy to use, i try in a30 gpu for 18 frame

shahiduljahid

Feb 7, 2025

@n3xt1lxs bro . I need some resources for fine-tune video-llava or any other VLM for videos. I have RTX 4090 locally. That's my email: shahiduljahid71@gmail.com. Can you share some resources with me like blogs, code references, or tutorials? that will be helpful. thanks bro .

n3xt1lxs

Feb 21, 2025

@n3xt1lxs bro . I need some resources for fine-tune video-llava or any other VLM for videos. I have RTX 4090 locally. That's my email: shahiduljahid71@gmail.com. Can you share some resources with me like blogs, code references, or tutorials? that will be helpful. thanks bro .

I'm sorry for the late reply. There was no notification. I had to check on huggıngface myself.
can go talk in discord? if you can , add me discord : n3xt1lxs

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