RLVER
/

PPO-thinking

Model card Files Files and versions

https://www.arxiv.org/abs/2507.03112

Downloads last month: 4

Safetensors

Model size

7.62B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for RLVER/PPO-thinking

Base model

Qwen/Qwen2.5-7B

Finetuned

Qwen/Qwen2.5-7B-Instruct

Finetuned

(2423)

this model

Collection including RLVER/PPO-thinking

RLVER

Checkpoints trained via RLVER, the first RLVR framework to boost LLM empathy. • 4 items • Updated 1 day ago