AI model distillation (learning)¶
| Field | Value |
|---|---|
| Status | Active |
| Type | Personal learning / research |
Description¶
A personal learning project on model distillation: training smaller or cheaper student models to approximate a larger teacher (or ensemble), including classic knowledge distillation, logits matching, and related compression ideas. Goal is hands-on understanding of how distilled models behave, fail, and trade off quality vs. cost — not a product launch.
Structured multi-phase plan (full verbatim checklist): raw/ai-model-distillation-learning-plan.md.
Learning plan (progress)¶
| Phase | Focus | Milestone | Status |
|---|---|---|---|
| 1 | Foundation: Moonshot (Alex Wissner-Gross), paper(s), distillation-minded hands-on (see education-startup-ux / Boxy) | Grounding + one applied thread | Done |
| 2 | Generalize beyond the podcast via LLM prompts; save generalization doc; tie to your skills | Personalized 2–3 page summary | Not started |
| 3 | Read 8–12 resources: Hinton KD, distilling step-by-step, HF guides, OpenAI distillation tutorial, DistillKit/notebooks, search + alerts | Notion/Zotero (or equivalent) with highlights + snippets | Not started |
| 4 | Build a narrow student (OpenAI distillation path or open-source teacher → HF/DistillKit); deploy + case study | Live demo + 1-page “cost / niche metric” writeup | Not started |
Phase 2 (next) — outline¶
- One broad prompt: mechanisms (response / logit KD / synthetic data), economics, beyond LLMs, iterated loops, examples (e.g. Phi, OpenAI distillation API), 3–5 student niche ideas.
- 3–5 follow-ups (e.g. apply to medicine, law, coding).
- Deliverable: full thread saved + 2–3 page personalized summary.
Phase 3 — outline¶
- Papers: Hinton 2015 “Distilling the Knowledge…”; “Distilling step-by-step” (Google + Snorkel, 2023); HF KD + CV distillation material.
- Hands-on tutorials: OpenAI distillation guide (GPT-4o → mini); Snorkel/Labelbox intros; Arcee DistillKit / Nebius notebooks.
- Search habit: HF + synthetic-data queries; arXiv (“scaling laws”, “reinforcement-aware KD”); alerts/RSS for “model distillation.”
Phase 4 — outline¶
- Pick a narrow problem where you have edge (domain reviewer, tutor, clause explainer, etc.).
- Fast path: OpenAI API, synthetic data from teacher, distill to mini, fine-tune, held-out eval.
- OSS path: Large teacher on Groq/HF, synthetic rationales, Transformers + DistillKit / distillation
Trainer, optional quantize/prune. - Ship: Space/Vercel/Replicate, short social post + 1-page case study.
Origin / how it connected to work¶
- Sources: Listened repeatedly to Moonshot episodes featuring Alex Wissner-Gross’s explanation of model distillation, plus reading a paper on the topic.
- Application: Tried a rudimentary, distillation-minded approach on the education startup problem — on-device coaching (smaller / adapted models, including Distil-Whisper-style paths and lighter transcription) alongside a custom baby-coo detector — documented under education-startup-ux as the Boxy POC.
- Lesson: For full video coaching quality, Gemini on uploaded video already met the bar; the local stack was valuable for feasibility + UX experiments, not as the long-term substitute for that coaching depth.
Key features / scope¶
- Theory + practice: core papers, podcasts, and targeted experiments (including work-adjacent POCs where ethical and appropriate).
- Distinction: This page tracks personal learning; Boxy implementation detail lives on education-startup-ux.
Tech stack¶
- Study: general PyTorch / HF / PEFT ecosystem; Whisper family and distilled variants appeared in the work POC (see education page).
- Phase 4: OpenAI distillation API vs. DistillKit / HF — choose when you start build.
- Add dedicated personal repo or notebook links in
raw/when you want them canonical.
Raw sources¶
raw/ai-model-distillation-learning-plan.md— phased checklist (Phases 2–4 verbatim + Phase 1 note).raw/education-startup-boxy-poc.md— technical thread (Distil-Whisper LoRA, coo CNN, Core ML) tied to the work POC informed by this study.
Related¶
- llm-maintained-context — wiki maintenance practice used to track this work.
- ../What-Im-Working-On — public snapshot.
- education-startup-ux — Boxy on-device exploration and Gemini prototype; distillation intuition applied here before the cloud pivot.
Known issues¶
- Phase 2–4 deliverables (generalization doc, Zotero/Notion library, shipped student + case study) not linked here yet.