Instructions to use giobin/idefics2_random_connector with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use giobin/idefics2_random_connector with Transformers:

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

pipe = pipeline("image-text-to-text", model="giobin/idefics2_random_connector")

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("giobin/idefics2_random_connector")
model = AutoModelForMultimodalLM.from_pretrained("giobin/idefics2_random_connector", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use giobin/idefics2_random_connector with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "giobin/idefics2_random_connector"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "giobin/idefics2_random_connector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/giobin/idefics2_random_connector

SGLang

How to use giobin/idefics2_random_connector 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 "giobin/idefics2_random_connector" \
    --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": "giobin/idefics2_random_connector",
		"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 "giobin/idefics2_random_connector" \
        --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": "giobin/idefics2_random_connector",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use giobin/idefics2_random_connector with Docker Model Runner:
```
docker model run hf.co/giobin/idefics2_random_connector
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

This model uses the architecture of Idefics2 with loaded trained backbones (Mistral 7b and Siglip) but random connector. This model is intended as a pre-training starting point

Downloads last month: 2

Safetensors

Model size

8B params

Tensor type

F32

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support