Instructions to use liuhaotian/llava-v1.6-vicuna-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use liuhaotian/llava-v1.6-vicuna-7b with Transformers:

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

pipe = pipeline("image-text-to-text", model="liuhaotian/llava-v1.6-vicuna-7b")

# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("liuhaotian/llava-v1.6-vicuna-7b")
model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-v1.6-vicuna-7b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use liuhaotian/llava-v1.6-vicuna-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "liuhaotian/llava-v1.6-vicuna-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "liuhaotian/llava-v1.6-vicuna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/liuhaotian/llava-v1.6-vicuna-7b

SGLang

How to use liuhaotian/llava-v1.6-vicuna-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 "liuhaotian/llava-v1.6-vicuna-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": "liuhaotian/llava-v1.6-vicuna-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 "liuhaotian/llava-v1.6-vicuna-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": "liuhaotian/llava-v1.6-vicuna-7b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use liuhaotian/llava-v1.6-vicuna-7b with Docker Model Runner:
```
docker model run hf.co/liuhaotian/llava-v1.6-vicuna-7b
```

AutoModelForCausalLM.from_pretrained("liuhaotian/llava-v1.6-vicuna-7b") fail

by thlw - opened May 30, 2024

Discussion

thlw

May 30, 2024

when i use model = AutoModelForCausalLM.from_pretrained("liuhaotian/llava-v1.6-vicuna-7b"),i got
Unrecognized configuration class <class 'transformers.models.llava.configuration_llava.LlavaConfig'> for this kind of AutoModel: AutoModelForCausalLM.

hazemabbas1

Jun 10, 2024

Same Issue

friedrichor

Jul 4, 2024

This version only allows loading via the code in the github repository (https://github.com/LLaVA-VL/LLaVA-NeXT) and not via the transformers.
https://huggingface.co/llava-hf/llava-v1.6-vicuna-7b-hf Here is the hf version of the model weights, which can be loaded directly via AutoModelForCausalLM.
For another approach, refer to https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava_next/convert_llava_next_weights_to_hf.py converts this version of weights to the hf version.

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