YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Gemma 2 2B - QA-SFT (closed-book, calibrated)

LoRA fine-tune of google/gemma-2-2b-it for closed-book QA with knowledge-boundary calibration (R-Tuning): answer what it knows, abstain otherwise. Reaches parity with base on a closed-book knowledge eval (4.5 vs 4.5); the RAG variant is the one that beats base.

Downloads last month
19
Safetensors
Model size
3B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for thesreedath/gemma-2-2b-qa-sft

Adapters
1 model