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
```

nielsr HF Staff commited on May 16, 2024

Commit

4cf9d8c

verified ·

1 Parent(s): 68ecfc2

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

@@ -17,6 +17,11 @@ Base LLM: [lmsys/vicuna-13b-v1.5](https://huggingface.co/lmsys/vicuna-13b-v1.5)
 The model can generate interleaving images and videos, despite the absence of image-video pairs in the dataset. Video-LLaVa is uses an encoder trained for unified visual representation through alignment prior to projection.
 Extensive experiments demonstrate the complementarity of modalities, showcasing significant superiority when compared to models specifically designed for either images or videos.
 **Paper or resources for more information:**
 https://github.com/PKU-YuanGroup/Video-LLaVA

 The model can generate interleaving images and videos, despite the absence of image-video pairs in the dataset. Video-LLaVa is uses an encoder trained for unified visual representation through alignment prior to projection.
 Extensive experiments demonstrate the complementarity of modalities, showcasing significant superiority when compared to models specifically designed for either images or videos.
+<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/videollava_example.png"
+alt="drawing" width="600"/>
+<small> VideoLLaVa example. Taken from the <a href="https://arxiv.org/abs/2311.10122">original paper.</a> </small>
 **Paper or resources for more information:**
 https://github.com/PKU-YuanGroup/Video-LLaVA