Image-Text-to-Text
Transformers
Safetensors
English
llava_next
vision
conversational
text-generation-inference
Instructions to use llava-hf/llava-v1.6-34b-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llava-hf/llava-v1.6-34b-hf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="llava-hf/llava-v1.6-34b-hf") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("llava-hf/llava-v1.6-34b-hf") model = AutoModelForMultimodalLM.from_pretrained("llava-hf/llava-v1.6-34b-hf", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] 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=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use llava-hf/llava-v1.6-34b-hf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "llava-hf/llava-v1.6-34b-hf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "llava-hf/llava-v1.6-34b-hf", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/llava-hf/llava-v1.6-34b-hf
- SGLang
How to use llava-hf/llava-v1.6-34b-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 "llava-hf/llava-v1.6-34b-hf" \ --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": "llava-hf/llava-v1.6-34b-hf", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'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 "llava-hf/llava-v1.6-34b-hf" \ --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": "llava-hf/llava-v1.6-34b-hf", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use llava-hf/llava-v1.6-34b-hf with Docker Model Runner:
docker model run hf.co/llava-hf/llava-v1.6-34b-hf
why the output only contains "\n"???
2
#20 opened about 2 years ago
by
miaoyl
Error - Image mismatch number of tokens in prompt and number of images passe
2
#18 opened over 2 years ago
by
Koshti10
The tokenizer config does not match the version shared by the original author
🔥 1
1
#17 opened over 2 years ago
by
GohioAC
Inference very slow on A100
2
#16 opened over 2 years ago
by
JehandBrs
Inference taking 2 or 3 minutes on A100
2
#15 opened over 2 years ago
by
karthikeyanvijayan
Inference taking so long
2
#14 opened over 2 years ago
by
J812
Error Deploying on SageMaker
#12 opened over 2 years ago
by
wamozart
Update Transformers version in config.json
#11 opened over 2 years ago
by
barleyspectacular
inference with follow up questions
1
#10 opened over 2 years ago
by
lzh986
ValueError: The input provided to the model are wrong. The number of image tokens is 1 while the number of image given to the model is 1. This prevents correct indexing and breaks batch generation.
29
#8 opened over 2 years ago
by
bghira
How do you fine tune LLaVA NeXT?
33
#5 opened over 2 years ago
by
Nishgop