Instructions to use HuggingFaceM4/idefics-80b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/idefics-80b with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceM4/idefics-80b")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics-80b")
model = AutoModelForImageTextToText.from_pretrained("HuggingFaceM4/idefics-80b")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/idefics-80b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/idefics-80b"
# 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-80b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/idefics-80b

SGLang

How to use HuggingFaceM4/idefics-80b 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-80b" \
    --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-80b",
		"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-80b" \
        --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-80b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/idefics-80b with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/idefics-80b
```

stas commited on Aug 22, 2023

Commit

a0bb871

1 Parent(s): 2ccbe9d

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -2

README.md CHANGED Viewed

@@ -305,11 +305,15 @@ Similarly to the base IDEFICS models, we performed checkpoint selection to stop
 ## Hardware
-The IDEFICS models were trained on an AWS SageMaker cluster using at the maximum 64 nodes of 8x80GB A100 GPUs (512 GPUs total). The cluster uses the current EFA network. IDEFICS-80b was trained for approximately 672 node hours. IDEFICS-80b-instruct was trained for approximately 3 days on 48 nodes.
 ## Software
-The training software is built on top of HuggingFace Transformers + Accelerate, and DeepSpeed ZeRO-3 for training, and [WebDataset](https://github.com/webdataset/webdataset) for data loading.
 # Bias, Risks, and Limitations

 ## Hardware
+The IDEFICS models were trained on an AWS SageMaker cluster with 8x80GB A100 GPUs nodes and EFA network.
+- IDEFICS-80B took ~28 days of training on 64 nodes (512 GPUs).
+- IDEFICS-80b-instruct finetuned the base model for ~3 days on 48 nodes (384 GPUs).
 ## Software
+The training software is built on top of HuggingFace Transformers + Accelerate, and [DeepSpeed ZeRO-3](https://github.com/microsoft/DeepSpeed) for training, and [WebDataset](https://github.com/webdataset/webdataset) for data loading.
 # Bias, Risks, and Limitations