Instructions to use HuggingFaceM4/idefics-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/idefics-9b with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceM4/idefics-9b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics-9b")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceM4/idefics-9b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/idefics-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/idefics-9b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/idefics-9b

SGLang

How to use HuggingFaceM4/idefics-9b 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 "HuggingFaceM4/idefics-9b" \
    --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": "HuggingFaceM4/idefics-9b",
		"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 "HuggingFaceM4/idefics-9b" \
        --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": "HuggingFaceM4/idefics-9b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/idefics-9b with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/idefics-9b
```

Requirements for running the model

by vishaal27 - opened Aug 24, 2023

Discussion

vishaal27

Aug 24, 2023

•

edited Aug 24, 2023

Maybe this is something that is well known, but I had a few issues while running the model, and I just wanted to share my final environment settings that got it working on an NVIDIA A100-40GB GPU.

conda create --name ideficsenv python=3.8 -y
conda activate ideficsenv

# for idefics install specific transformers version
pip install transformers==4.32.0
# for A100 nodes, I had to setup torch specifically to use cu110+ compiles, idefics requires torch 2.0.0+
pip install torch==2.0.1+cu117 torchvision==0.15.2+cu117 -f https://download.pytorch.org/whl/torch_stable.html
# idefics also requires sentencepiece, protobuf, scipy, bitsandbytes and accelerate
pip install sentencepiece
pip install protobuf
pip install scipy bitsandbytes accelerate

With this setup, I was able to run the example inference script without any issues.

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