Instructions to use ayoubkirouane/Idefics2-8b-Finetuned-Lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ayoubkirouane/Idefics2-8b-Finetuned-Lora with Transformers:

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

pipe = pipeline("image-text-to-text", model="ayoubkirouane/Idefics2-8b-Finetuned-Lora")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ayoubkirouane/Idefics2-8b-Finetuned-Lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ayoubkirouane/Idefics2-8b-Finetuned-Lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ayoubkirouane/Idefics2-8b-Finetuned-Lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ayoubkirouane/Idefics2-8b-Finetuned-Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ayoubkirouane/Idefics2-8b-Finetuned-Lora

SGLang

How to use ayoubkirouane/Idefics2-8b-Finetuned-Lora 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 "ayoubkirouane/Idefics2-8b-Finetuned-Lora" \
    --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": "ayoubkirouane/Idefics2-8b-Finetuned-Lora",
		"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 "ayoubkirouane/Idefics2-8b-Finetuned-Lora" \
        --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": "ayoubkirouane/Idefics2-8b-Finetuned-Lora",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ayoubkirouane/Idefics2-8b-Finetuned-Lora with Docker Model Runner:
```
docker model run hf.co/ayoubkirouane/Idefics2-8b-Finetuned-Lora
```

Base Model :

HuggingFaceM4/idefics2-8b

Dataset :

nielsr/docvqa_1200_examples

Get started :


from transformers import AutoModelForCausalLM
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/idefics2-8b")
peft_model_id = "ayoubkirouane/Idefics2-8b-Finetuned-Lora"
model = PeftModel.from_pretrained(base_model, peft_model_id)

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

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

ayoubkirouane
/

Idefics2-8b-Finetuned-Lora

Base Model :

Dataset :

Get started :

Dataset used to train ayoubkirouane/Idefics2-8b-Finetuned-Lora