metadata

license: mit
license_link: https://huggingface.co/OpenPipe/Deductive-Reasoning-Qwen-14B/blob/main/LICENSE
language:
  - zho
  - eng
  - fra
  - spa
  - por
  - deu
  - ita
  - rus
  - jpn
  - kor
  - vie
  - tha
  - ara
pipeline_tag: text-generation
base_model:
  - Qwen/Qwen2.5-14B-Instruct
tags:
  - chat
library_name: transformers

Deductive-Reasoning-Qwen-14B

Deductive Reasoning Qwen 14B is a reinforcement fine-tune of Qwen 2.5 14B Instruct to solve challenging deduction problems from the Temporal Clue dataset, trained by OpenPipe!

Here are some additional resources to check out:

Blog Post
Training Recipe
RL Experiments
Deductive Reasoning Qwen 32B

If you're interested in training your own models with reinforcement learning or just chatting, feel free to reach out or email Kyle directly at [email protected]!