---
base_model: meta-llama/Llama-3.2-3B-Instruct
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 C 3B.

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

Go to the [model page](https://huggingface.co/piotr25691/thea-c-3b-25r) to find out what Thea is.