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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics-9b-instruct"
# 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-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

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

SGLang

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

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

Code for instruction tuning

#10

by schwarzwalder - opened Jan 18, 2024

Discussion

schwarzwalder

Jan 18, 2024

•

edited Jan 18, 2024

Hi Team,

Could you please provide the code used for instruction fine-tuning the base model ?

I have checked the examples in here - https://github.com/huggingface/notebooks/tree/main/examples/idefics , but I suppose these are for normal fine-tuning using image-text pairs (interleaved) with next token prediction task.
inputs["labels"] = inputs["input_ids"]

I am specifically interested to know the changes required in the input/output processors for fine tuning on VQA datasets (which requires a conditional generation task given the image + question) ?

Thanks in advance.

schwarzwalder

Jan 18, 2024

@VictorSanh @HugoLaurencon FYI

VictorSanh

Jan 18, 2024

Hi @VishnuSuganth
We have not released the codebase we used to train and perform sft for idefics (mostly because we don't have the bandwidth of maintaining this codebase).
However the fine-tuning script will give you a good start!
The exact formatting we used to fine-tune on vqa datasets is essentially the same as what you see for inference:

User: {question}{image}<end_of_utterance>\nAssistant: {answer}<end_of_utterance>

schwarzwalder

Jan 18, 2024

Ok thanks. Can you also share some information on how to set the input[“labels”] for sft and changes to the loss computation in the forward function ?

VictorSanh

Jan 18, 2024

No changes on the loss, standard next token prediction!
We did not limit the loss computation to the answer, but that could be a fun thing to sanity-try.

schwarzwalder

Jan 23, 2024

@VictorSanh Thank you.

schwarzwalder changed discussion status to closed Jan 23, 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