thesreedath

slm-gemma-2b-dpo2

thesreedath/slm-gemma-2b-dpo2

slm-gemma-2b-dpo2 is a machine learning model from thesreedath. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.

Gemma 2 2B: gemma-2-2b-it - QA SFT - instruction SFT - DPO v2 (QLoRA, beta=0.1) on ~4k AI-feedback preference pairs spanning closed-book QA AND instruction-following failure modes, prompts held out of both SFT sets.