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
```

LanguageBind commited on Feb 18, 2024

Commit

b1d6a63

verified ·

1 Parent(s): 0d50857

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -6

config.json CHANGED Viewed

@@ -1,8 +1,4 @@
 {
-  "X": [
-    "Video",
-    "Image"
-  ],
   "_name_or_path": "lmsys/vicuna-7b-v1.5",
   "architectures": [
     "LlavaLlamaForCausalLM"
@@ -20,8 +16,8 @@
   "mm_hidden_size": 1024,
   "mm_image_tower": "LanguageBind/LanguageBind_Image",
   "mm_projector_type": "mlp2x_gelu",
-  "mm_use_x_patch_token": false,
-  "mm_use_x_start_end": false,
   "mm_video_tower": "LanguageBind/LanguageBind_Video_merge",
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -2,

 {
   "_name_or_path": "lmsys/vicuna-7b-v1.5",
   "architectures": [
     "LlavaLlamaForCausalLM"
   "mm_hidden_size": 1024,
   "mm_image_tower": "LanguageBind/LanguageBind_Image",
   "mm_projector_type": "mlp2x_gelu",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
   "mm_video_tower": "LanguageBind/LanguageBind_Video_merge",
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -2,