geolip-aleph-diffusion / REPO_MAP.md
AbstractPhil's picture
REPO_MAP accuracy fix (qwen-line ckpt claim scoped to shipped weights; kept identical to the qwen copy)
24026b5 verified
|
Raw
History Blame Contribute Delete
3.68 kB

Repo map — the geolip-aleph program

The Qwen (language) line

repo what it is what you take from it maturity
geolip-aleph-qwen-3.5-0.8b-instruct the research record (the ft3 campaign): 19 experiment packages, raw ledgers, audits, retractions, article_ft3.md, campaign_ledger.jsonl the evidence — every claim's receipts; checkpoints under */ckpt/ where weights shipped (inference-only batteries and the two disclosed pod-lost sets have none) complete, frozen at campaign close
qwen3.5-0.8b-relay-caption production caption adapter for Qwen/Qwen3.5-0.8B relay_caption.py + both seed checkpoints; validated end-to-end (artifact + loader gates PASS, off-pod quickstart) usable; know the e004e trade-off (detach for structured vision tasks)
geolip-aleph-qwen the Qwen2.5-0.5B predecessor line (exp001–014 there) + article_ft2.md the two-regime dispatch law's first certification; the ft2 article complete (prior campaign)
qwen-deepfashion-fused the fused image dataset (captions + per-task JSON GT + entity polygons) training/eval data for the caption line AND the diffusion line's fused-data + blob targets stable

The diffusion line (runner 2)

repo what it is what you take from it maturity
geolip-aleph-diffusion the research record (the 3-D campaign): 16 experiment packages + substrate, 2-seed program, article_ft3d.md, all adapter weights (.pt + verified .safetensors) the evidence — the conditioning law, relay 3-for-3, the multiband mechanism, the routing falsifications complete, frozen at campaign close
aleph-diffusion-adapters production adapters (curated safetensors: sd15 core relay + multiband, lune-flow blob stack, anima relay) attachable artifacts with provenance metadata; the quickstart usable at research grade; per-row evidence status on the card; anima NC
amoe-lora the framework, now both substrate families: LM verbs + amoe.diffusion (relay/multiband/StepGatedSampler, safetensors I/O, amoe-convert) the amoe package (pip -e .[diffusion]); invariant-tested incl. dtype law; every campaign checkpoint format loads 0.2 working-state; train reference-grade; DDP untested >1 GPU; FSDP non-goal; ComfyUI node next
diffusion-pipe fork the multi-GPU trainer with aleph baked into main (cosmos/anima relay+multiband, SDXL relay; amoe-format saves; pure-Adam guard) aleph_relay = true in any supported TOML; examples/aleph_*.toml proven end-to-end on Anima (exp004); SDXL path landed, site count pins at first run; multiband stages>1 deferred

Articles: ft1 (byte-level origins) → ft2 (Qwen2.5: two-regime law) → ft3 (Qwen3.5 VLM: the regime law at family scale) → ft3d (diffusion: the conditioning law).