thomasjhuang
/

qwen2-rloo-countdown-step250

Text Generation

reinforcement-learning

Model card Files Files and versions

qwen2-rloo-countdown-step250 / added_tokens.json

thomasjhuang's picture

RLOO checkpoint at optimizer step 250 - Fixed prompt format, temp=0.1, lr=3e-6

e4ad155 verified 11 months ago

history blame contribute delete

80 Bytes

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