Instructions to use lmms-lab/LLaVA-NeXT-Video-34B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lmms-lab/LLaVA-NeXT-Video-34B with Transformers:

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

pipe = pipeline("text-generation", model="lmms-lab/LLaVA-NeXT-Video-34B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("lmms-lab/LLaVA-NeXT-Video-34B")
model = AutoModelForCausalLM.from_pretrained("lmms-lab/LLaVA-NeXT-Video-34B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use lmms-lab/LLaVA-NeXT-Video-34B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lmms-lab/LLaVA-NeXT-Video-34B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmms-lab/LLaVA-NeXT-Video-34B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/lmms-lab/LLaVA-NeXT-Video-34B

SGLang

How to use lmms-lab/LLaVA-NeXT-Video-34B 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 "lmms-lab/LLaVA-NeXT-Video-34B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmms-lab/LLaVA-NeXT-Video-34B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "lmms-lab/LLaVA-NeXT-Video-34B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lmms-lab/LLaVA-NeXT-Video-34B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use lmms-lab/LLaVA-NeXT-Video-34B with Docker Model Runner:
```
docker model run hf.co/lmms-lab/LLaVA-NeXT-Video-34B
```

LLaVA-Next-Video Model Card

Model details

Model type:
LLaVA-Next-Video is an open-source chatbot trained by fine-tuning LLM on multimodal instruction-following data.
Base LLM: NousResearch/Nous-Hermes-2-Yi-34B

Model date:
LLaVA-Next-Video-34B was trained in April 2024.

Paper or resources for more information:
https://github.com/LLaVA-VL/LLaVA-NeXT

License

NousResearch/Nous-Hermes-2-Yi-34B license.

Where to send questions or comments about the model

https://github.com/LLaVA-VL/LLaVA-NeXT/issues

Intended use

Primary intended uses:
The primary use of LLaVA is research on large multimodal models and chatbots.

Primary intended users:
The primary intended users of the model are researchers and hobbyists in computer vision, natural language processing, machine learning, and artificial intelligence.

Training dataset

Image

558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP.
158K GPT-generated multimodal instruction-following data.
500K academic-task-oriented VQA data mixture.
50K GPT-4V data mixture.
40K ShareGPT data.

Video

100K VideoChatGPT-Instruct.

Evaluation dataset

A collection of 4 benchmarks, including 3 academic VQA benchmarks and 1 captioning benchmark.

Downloads last month: 79

Safetensors

Model size

35B params

Tensor type

BF16