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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics2-8b-base"
# 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-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

HugoLaurencon commited on Apr 12, 2024

Commit

0043d59

verified ·

1 Parent(s): 7b9186b

Typo

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -46,7 +46,7 @@ We release under the Apache 2.0 license 2 checkpoints:
 # Uses
-`idefics2-8b-base` and `idefics2-8b` can be used to perform inference on multimodal (image + text) tasks in which the input is compsed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.
 For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.

 # Uses
+`idefics2-8b-base` and `idefics2-8b` can be used to perform inference on multimodal (image + text) tasks in which the input is composed of a text query along with one (or multiple) image(s). Text and images can be arbitrarily interleaved. That includes image captioning, visual question answering, etc. These model does not support image generation.
 For optimal results, we recommend fine-tuning `idefics2-8b` on one's specific use-case and data. In fact, the instruction-fine-tuned model (`idefics2-8b`) is significantly better at following instructions from users and thus should be preferred when using the models out-of-the-box or as a starting point for fine-tuning.