this is not a base Llama 3.2 uncensored model

README.md

@@ -10,7 +10,7 @@ tags:
 - sft
 - reasoning
 - llama-3
-base_model: chuanli11/Llama-3.2-3B-Instruct-uncensored
+base_model: lunahr/Hermes-3-Llama-3.2-3B-abliterated
 datasets:
 - KingNish/reasoning-base-20k
 - lunahr/thea-name-overrides
@@ -65,4 +65,4 @@ print("ANSWER: " + response_output)
 
 This Llama model was trained faster than [Unsloth](https://github.com/unslothai/unsloth) using [custom training code](https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4).
 
-Visit https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.
+Visit https://www.kaggle.com/code/piotr25691/distributed-llama-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.