Haitao999
/

Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions Community

Llama-3.2-3B-Instruct-GRPO-numia_prompt_dpo1 / generation_config.json

Haitao999's picture

Model save

17bc122 verified 23 days ago

184 Bytes

	{
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": [
	128001,
	128008,
	128009
	],
	"temperature": 0.6,
	"top_p": 0.9,
	"transformers_version": "4.48.3"
	}