Views
No views yet
(document, position) in the source corpus.⚠️ Scope. This is not a general-purpose LLM. It was trained on a deliberately small research corpus (~16K documents: climate mechanics, astronomy, sleep science, Python docs, resume practice). Within that material it navigates coherently; outside it, it has nothing to navigate — the dataset you bring is the answers you get. The full bake pipeline ships here, so you can rebuild the artifact from your own texts.
| Planner parameters | 1.9 M (transformer encoder: 3 layers · d=192 · 4 heads, context 12 granules) |
| Artifact size | 1.99 GB |
| ─ granule embeddings | 0.98 GB (1.25M grains · MiniLM-384 · fp16) |
| ─ granule texts | ~0.8 GB (verbatim source fragments, µ/σ/Ω levels) |
| ─ document index | 24 MB (15,500 docs · 384d) |
| ─ planner weights | 8 MB |
| Granule bank | 723,990 usable grains after canonization/dedup masks |
| Semantics | all-MiniLM-L6-v2 → PCA 384→32 projection |
| Stylometry | 32-dim oscillator features + valence/arousal |
┌────────────────────────── OFFLINE: BAKE ──────────────────────────┐
│ │
corpus │ granulation semantics + style teacher demos │
┌──────────────┐ │ ┌──────────────┐ ┌──────────────────┐ ┌───────────────┐ │
│ raw web texts│─────▶│ │ µ micro │ │ MiniLM-384 sems │ │ ride planner │ │
└──────────────┘ │ │ σ meso │────▶ │ stylometry (32d) │ │ picks doc arc │ │
│ │ Ω macro │ │ affect (V/A) │ │ + corrections │ │
│ └──────────────┘ └────────┬─────────┘ └───────┬───────┘ │
│ syndication dedup │ │ │
│ canonization ▼ ▼ │
│ ┌──────────────────┐ ╔═══════════════════╗
│ │ oscillatory │ ║ DISTILLATION ║
│ │ field: clusters, ║──▶║ demo triples with ║
│ │ transitions, │ ║ correction moments│
│ │ grain bank │ ╚═══════════════════╝
│ └────────┬─────────┘ │ │
└────────────────────────────────┼──────────────────────┼──────────┘
▼ ▼
╔══════════════════════════════════════╗
║ brain.pt (1.9 GB) ║
║ planner weights · granule bank · ║
║ doc embeddings · quality masks ║
╚══════════════╦═══════════════════════╝
│
┌────────────────── INFERENCE: NO RETRIEVAL ─────────────────────────┐
│ │
"What causes │ ┌───────────┐ qsem token │
El Niño?" ────────┼───────▶│ question │───────┐ │
│ │ embedding │ ▼ │
│ │ ┌─────────────────────────┐ predict next-grain │
│ │ │ transformer over field │───embedding ──┐ │
│ │ │ state (+ working memory)│ │ snap │
│ │ └─────────────────────────┘ ▼ │
│ │ ┌─────────────────────┐ │
│ │ │ baked granule bank │ │
│ │ │ (nearest neighbor) │ │
│ │ └──────────┬──────────┘ │
│ │ repeat step ◀────────────────────┘ │
│ ▼ │
│ answer = stitched verbatim granules, each traceable to (doc, pos) │
└────────────────────────────────────────────────────────────────────┘1pip install -r requirements.txt
2
3# ask the baked brain
4python brain_chat.py --brain brain.pt --ask "What causes El Nino?"
5
6# interactive session
7python brain_chat.py --brain brain.pt --chat1python granulate.py # corpus → granules → semantics → field caches
2python gen_demos.py # teacher demonstrations (correction moments)
3python train_brain.py # distill teacher into the planner
4python bake_brain.py # pack everything into one brain.pt| file | purpose |
|---|---|
brain.pt | the baked artifact: planner weights + granule bank + doc embeddings + masks |
granular_text_field.py | core library: pool, semantics, oscillatory field, canonization |
brain_chat.py | inference shell: single ask / interactive session |
gen_demos.py | generates teacher demonstration triples |
train_brain.py | trains the planner (distillation + discriminative negatives) |
bake_brain.py | packs weights + memory into the single-file artifact |