arlarena
/

math_grpo

Model card Files Files and versions

math_grpo / huggingface /generation_config.json

xw27's picture

Upload complete AgentRL training checkpoint (direct files)

2c1cca8 verified about 1 month ago

history blame contribute delete

117 Bytes

	{
	"bos_token_id": 151643,
	"eos_token_id": 151643,
	"max_new_tokens": 2048,
	"transformers_version": "4.51.0"
	}