Instructions to use mohbattharani/LLaVA-Chef with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mohbattharani/LLaVA-Chef with Transformers:

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

pipe = pipeline("image-text-to-text", model="mohbattharani/LLaVA-Chef")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCausalLM

processor = AutoProcessor.from_pretrained("mohbattharani/LLaVA-Chef")
model = AutoModelForCausalLM.from_pretrained("mohbattharani/LLaVA-Chef", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mohbattharani/LLaVA-Chef with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mohbattharani/LLaVA-Chef

SGLang

How to use mohbattharani/LLaVA-Chef 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 "mohbattharani/LLaVA-Chef" \
    --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": "mohbattharani/LLaVA-Chef",
		"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 "mohbattharani/LLaVA-Chef" \
        --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": "mohbattharani/LLaVA-Chef",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mohbattharani/LLaVA-Chef with Docker Model Runner:
```
docker model run hf.co/mohbattharani/LLaVA-Chef
```

LLaVA-Chef

Commit History

Mar 24, 2025

21:06
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
b66ef8a

Mar 17, 2025

20:51
Upload pytorch_model-00002-of-00002.bin

mohbattharani

Verified signature
1bb948f
20:12
Upload pytorch_model-00001-of-00002.bin

mohbattharani

Verified signature
455798b
15:04
Update README.md

mohbattharani

Verified signature
f6ec0a0
15:03
Update config.json

mohbattharani

Verified signature
f8c6c4e
15:02
Upload 7 files

mohbattharani

Verified signature
d99a3da

Jul 24, 2024

20:38
initial commit

mohbattharani

Verified signature
242302e

Commit History

Mar 24, 2025

Adding `safetensors` variant of this model⁠

Mar 17, 2025

Upload pytorch_model-00002-of-00002.bin

Upload pytorch_model-00001-of-00002.bin

Update README.md

Update config.json

Upload 7 files

Jul 24, 2024

initial commit