AcademieDuNumerique
/

Llama-3.2-3B-ORPO-French-Reward-Instruct

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Llama-3.2-3B-ORPO-French-Reward-Instruct / config.json

Svngoku's picture

(Trained with Unsloth)

070876f verified 16 days ago

history blame contribute delete

29 Bytes

	{
	"model_type": "llama"
	}