xx18
/

TFPI-Qwen3-4B-Stage2

Text Generation

Model card Files Files and versions

README.md exists but content is empty.

Downloads last month: 6

Safetensors

Model size

4B params

Tensor type

BF16

·

Model tree for xx18/TFPI-Qwen3-4B-Stage2

Base model

Qwen/Qwen3-4B-Base

Finetuned

Finetuned

(451)

this model

Dataset used to train xx18/TFPI-Qwen3-4B-Stage2

Collection including xx18/TFPI-Qwen3-4B-Stage2

TFPI

ICLR2026: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners https://arxiv.org/abs/2509.26226 • 14 items • Updated 5 days ago