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
```

How to limit the loss computation to the answer ?

#44

by schwarzwalder - opened May 9, 2024

Discussion

schwarzwalder

May 9, 2024

•

edited May 9, 2024

In the idefics2 paper, there is a mention of computing the loss only for the answer part of the VQA task. I could not find such in the fine-tune colab.
Could you please provide a short snippet for that ?

Thanks in advance.

HugoLaurencon

May 13, 2024

Yesn it's true that it's not present in the google colab.

In our codebase, it is done in a hacky way in the packing, by tokenizing the input, getting the positions between Assistant: and the next <end_of_utterance>, and not computing the loss on those ids.

schwarzwalder

May 15, 2024

Thanks!

schwarzwalder changed discussion status to closed May 15, 2024

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