File size: 913 Bytes
f5fea3c 9dfbf98 f5fea3c |
1 2 3 4 5 6 7 8 9 10 11 12 13 |
🧪 Gemma-2B-DolphinR1-TestV2 (Experimental Fine-Tune) 🧪
This is an experimental fine-tune of Google's Gemma-2B using the [Dolphin-R1 dataset](https://huggingface.co/datasets/cognitivecomputations/dolphin-r1).
The goal is to enhance reasoning and chain-of-thought capabilities while maintaining efficiency with LoRA (r=32) and 4-bit quantization.
🚨 Disclaimer: This model is very much a work in progress and is still being tested for performance, reliability, and generalization. Expect quirks, inconsistencies, and potential overfitting in responses.
This is made possible thanks to @unsloth. I am still very new at finetuning Large Language Models so this is more of a showcase of my learning journey. Remember, it's very experimental, do not recommend downloading or testing. |