slm-500m-instr
500M legal SLM, instruction-tuned on top of thesreedath/slm-500m-qa (lineage: base -> closed-book QA SFT -> instruction SFT). Trained on ~6.5k domain-grounded synthetic 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
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support