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
```

How to use this model?

by pseudotensor - opened May 24, 2024

Discussion

pseudotensor

May 24, 2024

python -m sglang.launch_server --model-path lmms-lab/LLaVA-NeXT-Video-34B --port=30004 --host="0.0.0.0" --tp-size=1 --random-seed=1234 --context-length=8192

fails with:

/home/ubuntu/miniconda3/envs/sglang/lib/python3.10/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.
  warnings.warn(
config.json: 100%|???????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????| 1.80k/1.80k [00:00<00:00, 17.7MB/s]
/home/ubuntu/miniconda3/envs/sglang/lib/python3.10/site-packages/transformers/models/llava/configuration_llava.py:100: FutureWarning: The `vocab_size` argument is deprecated and will be removed in v4.42, since it can be inferred from the `text_config`. Passing this argument has no effect
  warnings.warn(
tokenizer_config.json: 100%|?????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????????| 1.62k/1.62k [00:00<00:00, 20.2MB/s]
Traceback (most recent call last):
  File "/home/ubuntu/miniconda3/envs/sglang/lib/python3.10/site-packages/huggingface_hub/utils/_errors.py", line 304, in hf_raise_for_status
    response.raise_for_status()
  File "/home/ubuntu/miniconda3/envs/sglang/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status
    raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-34B/resolve/main/preprocessor_config.json

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