An uncensored reasoning EXAONE 3.5 model trained on reasoning data. Now with a full epoch!

It has been trained using improved training code, and gives an improved performance. I'm uncertain whether it currently works. Check for a new version of Thea Pro later.

This Llama model was trained faster than Unsloth using custom training code.

Visit https://www.kaggle.com/code/piotr25691/distributed-hf-training-with-2xt4 to find out how you can finetune your models using BOTH of the Kaggle provided GPUs.