Downloads · 30 days
5
9% of all-time downloads
thesreedath/slm-125m-raft-dpo
slm-125m-raft-dpo 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 other.
125m legal SLM with RAFT (retrieval-augmented fine-tuning, Zhang et al. 2024): base - QA SFT - instruction SFT - DPO v2 - RAFT. Trained on ~14k examples of golden passage + 3 distractors (golden position uniform, 20%…
Downloads · 30 days
5
9% of all-time downloads
All-time downloads
54
Public
Parameters
126M
252 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors252 MB · 100%
From the Hugging Face model README
125m legal SLM with RAFT (retrieval-augmented fine-tuning, Zhang et al. 2024): base -> QA SFT -> instruction SFT -> DPO v2 -> RAFT. Trained on ~14k examples of golden passage + 3 distractors (golden position uniform, 20% no-golden refusals): answer from the right passage, ignore the noise, refuse when the context lacks the answer.