arlarena
/

if_step200

Reinforcement Learning

text-generation

instruction-following

text-generation-inference

Model card Files Files and versions

if_step200 / generation_config.json

xw27's picture

Qwen3-8B IFBench GRPO — iter 200 (last healthy pre-RM-outage checkpoint)

709b441 verified 18 days ago

History Blame Contribute Delete

138 Bytes

	{
	"bos_token_id": 151643,
	"do_sample": false,
	"eos_token_id": 151643,
	"max_new_tokens": 2048,
	"transformers_version": "4.37.0"
	}