longlian
/

Qwen2-0.5B-GRPO-peft-demo

Generated from Trainer

Model card Files Files and versions Community

Qwen2-0.5B-GRPO-peft-demo / added_tokens.json

longlian's picture

Training in progress, step 10

f91f181 verified about 1 month ago

history blame contribute delete

80 Bytes

	{
	"<\|endoftext\|>": 151643,
	"<\|im_end\|>": 151645,
	"<\|im_start\|>": 151644
	}