SFT details: instruction/reasoning/code/math mix, synthetic + human traces, no epoching
TimDarcet · x · 2026-10-21
TimDarcet described Muse Glimmer's SFT stage: instruction following, reasoning, code, math, and multistep tasks, using a mix of synthetic traces and human data, with no epoching. It's one step in the disclosed pipeline (pre-distill → mid-training → SFT → on-policy distill → RL).
More from Research
- Seqlet caller follow-up: credits for DeepLIFT contributors — jmschreiber91 · 2026-10-21
- Center for AI Safety Publishes Full Syllabus for Intro to ML Safety Course — ArtificialOther · 2026-10-21
- Seqlet caller gets 22x speedup: 167,750 loci drop from 7.8s to 0.35s — jmschreiber91 · 2026-10-21
- X trends: SophontAI's Holon-S1 predicts gene activity from cancer slides; decision models rise — iScienceLuvr · 2026-10-21
- NEJM AI study: LLM-recommended care costs up to 10x more than physician orders — dvir_a · 2026-10-21
- Nucleotide dependency analysis turns genomic language models into functional element detectors — jmschreiber91 · 2026-10-21