slm-gemma-2b-instr

Gemma 2 2B, instruction-tuned on top of thesreedath/slm-gemma-2b-qa (lineage: gemma-2-2b-it -> closed-book QA SFT -> instruction SFT). Trained on ~6.5k domain-grounded synthetic legal/financial instructions, every example compliance- and groundedness-judged. Loss on response tokens only.

Prompts may carry the working text inline after the instruction: <instruction>\n\nTEXT:\n<excerpt>.

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