metadata

base_model: chuanli11/Llama-3.2-3B-Instruct-uncensored
datasets:
  - KingNish/reasoning-base-20k
language:
  - en
license: llama3.2
library_name: peft
tags:
  - text-generation-inference
  - transformers
  - llama
  - trl
  - sft
  - reasoning
  - llama-3

Model Description

The LoRA adapters that pertain to 25% reasoned variant of Thea 3B.

You can merge them to your own Llama 3.2 3B, but why?

Go to the model page to find out what Thea is.