Instructions to use HuggingFaceM4/idefics2-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/idefics2-8b with Transformers:

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

pipe = pipeline("image-text-to-text", model="HuggingFaceM4/idefics2-8b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceM4/idefics2-8b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/idefics2-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics2-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/idefics2-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/idefics2-8b

SGLang

How to use HuggingFaceM4/idefics2-8b 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/idefics2-8b" \
    --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/idefics2-8b",
		"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/idefics2-8b" \
        --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/idefics2-8b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/idefics2-8b with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/idefics2-8b
```

Model is incompatible with Inference Endpoints

#23

by sebbyjp - opened Apr 18, 2024

Discussion

sebbyjp

Apr 18, 2024

2024/04/18 15:56:07 ~   File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py", line 1130, in from_pretrained
2024/04/18 15:56:07 ~     raise ValueError(
2024/04/18 15:56:07 ~ ValueError: The checkpoint you are trying to load has model type `idefics2` but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.
- 2024-04-18T19:56:07.898+00:00 
2024/04/18 15:56:07 ~ Application startup failed. Exiting.

Has the transformer version on the Inference Endpoints not been updated?

VictorSanh

Apr 18, 2024

hi @sebbyjp
let me circle back. transformers 4.40.0 was released just a few hours ago.

VictorSanh

Apr 19, 2024

Hi @sebbyjp ,
Here's the answer from the team:

We don't support multimodal pipelines in the toolkit wihtout a custom handler. So they need to create a handler.py and can add a requirements.txt.
They should see this warning message before deploying, that references the need for a custom handler

reference doc: https://huggingface.co/docs/inference-endpoints/guides/custom_handler

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