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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

VictorSanh commited on Aug 21, 2023

Commit

9709489

1 Parent(s): ab46de7

Update readme and doc from the 80b repo

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -408,7 +408,7 @@ Intentionally using the model for harm, violating [human rights](https://hugging
 The model is built on top of two pre-trained models: [laion/CLIP-ViT-H-14-laion2B-s32B-b79K](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) and [huggyllama/llama-65b](https://huggingface.co/huggyllama/llama-65b). The first was released under an MIT license, while the second was released under a specific non-commercial license focused on research purposes. As such, users should comply with that license by applying directly to [Meta's form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform).
-We release the additional weights we trained under an MIT license. The additional weights are randomly initialized parameters and trained, these are not based on any of the two base frozen models forming the composite model.
 # Citation

 The model is built on top of two pre-trained models: [laion/CLIP-ViT-H-14-laion2B-s32B-b79K](https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K) and [huggyllama/llama-65b](https://huggingface.co/huggyllama/llama-65b). The first was released under an MIT license, while the second was released under a specific non-commercial license focused on research purposes. As such, users should comply with that license by applying directly to [Meta's form](https://docs.google.com/forms/d/e/1FAIpQLSfqNECQnMkycAp2jP4Z9TFX0cGR4uf7b_fBxjY_OjhJILlKGA/viewform).
+The two pre-trained models are connected to each other with newly initialized parameters that we train. These are not based on any of the two base frozen models forming the composite model. We release the additional weights we trained under an MIT license.
 # Citation