Qwen2.5-7B-Instruct-QwQ

A QwQ style model trained from Qwen/Qwen2.5-7B-Instruct

1.7 epoch on PowerInfer/QWQ-LONGCOT-500K and PowerInfer/LONGCOT-Refine-500K
recommended parameters: temperature=0.7 top_p=0.8 repetition_penalty=1.1 max_tokens=16384
AIME24: 35.33% (average of 5 runs)

Safetensors

Model size

7.62B params

Tensor type

F32

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Model tree for tugstugi/Qwen2.5-7B-Instruct-QwQ-v0.1

Base model

Qwen/Qwen2.5-7B

Finetuned

Finetuned

(498)

this model

Quantizations