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

Libraries

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

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

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

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("HuggingFaceM4/idefics2-8b-AWQ")
model = AutoModelForMultimodalLM.from_pretrained("HuggingFaceM4/idefics2-8b-AWQ")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

idefics2-8b-AWQ / config.json

VictorSanh

forgot to rename modules not to convert

b56a945 about 2 years ago

Raw

History Blame Contribute Delete

959 Bytes

	{
	"architectures": [
	"Idefics2ForConditionalGeneration"
	],
	"image_token_id": 32001,
	"model_type": "idefics2",
	"perceiver_config": {
	"model_type": "idefics2"
	},
	"quantization_config": {
	"bits": 4,
	"group_size": 128,
	"modules_to_not_convert": ["model.vision_model", "model.connector.modality_projection", "model.connector.perceiver_resampler"],
	"quant_method": "awq",
	"version": "gemm",
	"zero_point": true
	},
	"text_config": {
	"max_position_embeddings": 32768,
	"model_type": "mistral",
	"pad_token_id": 0,
	"rms_norm_eps": 1e-05,
	"vocab_size": 32003
	},
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.40.0.dev0",
	"use_cache": true,
	"vision_config": {
	"hidden_size": 1152,
	"image_size": 980,
	"intermediate_size": 4304,
	"model_type": "idefics2",
	"num_attention_heads": 16,
	"num_hidden_layers": 27,
	"patch_size": 14
	}
	}