metadata
library_name: transformers
datasets:
- PowerInfer/QWQ-LONGCOT-500K
- PowerInfer/LONGCOT-Refine-500K
base_model:
- Qwen/Qwen2.5-7B-Instruct
license: apache-2.0
language:
- zho
- eng
- fra
- spa
- por
- deu
- ita
- rus
- jpn
- kor
- vie
- tha
- ara
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)