xx18
/

TFPI-Qwen3-4B-Thinking-2507-Stage3

Text Generation

Model card Files Files and versions

README.md exists but content is empty.

Downloads last month: 23

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

(150)

this model

Dataset used to train xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3

Collection including xx18/TFPI-Qwen3-4B-Thinking-2507-Stage3

TFPI

Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners • 14 items • Updated Nov 7, 2025