yangzhch6
/

Qwen2.5-Math-7B-L

Text Generation

text-generation-inference

Model card Files Files and versions

Follwoing LUFFY, we change to rope_theta from 10000 to 40000 and extend the context window to 16k.

Downloads last month: 7

Safetensors

Model size

8B params

Tensor type

F32

·

Model tree for yangzhch6/Qwen2.5-Math-7B-L

Quantizations

1 model

Collection including yangzhch6/Qwen2.5-Math-7B-L

Mirror-Critique

Critique to Verify: Accurate and Honest Test-Time Scaling with RL-Trained Verifiers (https://arxiv.org/abs/2509.23152) • 7 items • Updated Oct 4