Guess who's back! I set up a few things to train and automatically upload while I was gone but I forgot about the private repo storage limits so I'm setting this to public. I have no idea how well this works since I'm going to be using it for GRPO. It's probably not great!

Uploaded finetuned model

  • Developed by: DrRiceIO7
  • License: apache-2.0
  • Finetuned from model : unsloth/gemma-3-4b-pt-unsloth-bnb-4bit

This gemma3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month
101
Safetensors
Model size
4B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for DrRiceIO7/Gemma3-4B-CoT

Finetuned
(104)
this model
Quantizations
1 model