ReasoningTransferability
/

UniReason-Qwen3-14B-no-think-SFT

Text Generation

transferability

Distill from Qwen3-32B-Instruct (non-thinking mode) through Reject Sampling

text-generation-inference

Model card Files Files and versions

UniReason-Qwen3-14B-no-think-SFT / generation_config.json

Ibisbill's picture

Upload model from paper: Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

ab9d06d verified 18 days ago

history blame contribute delete

117 Bytes

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