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
```

Comment on image splitting

by HugoLaurencon - opened Apr 16, 2024

base: refs/heads/main

←

from: refs/pr/4

Discussion Files changed

-0

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -223,6 +223,8 @@ Given the high resolution supported, the vision part of the model can be memory
 - **deactivate the image splitting.** To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the sft model has been trained with image splitting.
 - **decrease the maximum image resolution.** To do so, add `size= {"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need. We recommend using values that are multiples of 14. There are no changes required on the model side.
 **Using Flash-attention 2 to speed up generation**
 <details><summary>Click to expand.</summary>

 - **deactivate the image splitting.** To do so, add `do_image_splitting=False` when initializing the processor (`AutoProcessor.from_pretrained`). There are no changes required on the model side. Note that only the sft model has been trained with image splitting.
 - **decrease the maximum image resolution.** To do so, add `size= {"longest_edge": 448, "shortest_edge": 378}` when initializing the processor (`AutoProcessor.from_pretrained`). In particular, the `longest_edge` value can be adapted to fit the need. We recommend using values that are multiples of 14. There are no changes required on the model side.
+`do_image_splitting=True` is especially needed to boost performance on OCR tasks where a very large image is used as input. For the regular VQA or captioning tasks, this argument can be safely set to `False` with minimal impact on performance (see the evaluation table above).
 **Using Flash-attention 2 to speed up generation**
 <details><summary>Click to expand.</summary>