junnyu / Qwen2.5-7B-Instruct-1M-GRPO_logic_KK_5PPL
Text Generation7.6B210Updated Feb 13, 2025
Downloads
21
Likes
0
Last updated
Feb 13, 2025
License
Not available
This model is a fine-tuned version of Qwen/Qwen2.5-7B-Instruct-1M on the KK-5PPL dataset. It has been trained using Unakar/Logic-RL.
Tasks & library
- text generation
- transformers
Tags
- transformers
- qwen2
- text-generation
- verl
- grpo
- conversational
Technical specifications
Parameters7.6B
Librarytransformers
LanguagesNot available
Base modelQwen/Qwen2.5-7B-Instruct-1M
LicenseNot available