Downloads · 30 days
0
3-adic-vae-checkpoints
geestaltt/3-adic-vae-checkpoints
3-adic-vae-checkpoints is a machine learning model from geestaltt. 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 mit.
Archives the training-run checkpoints that CLAUDE.md in the source repo (https://github.com/gesttaltt/3-adic-ml) cites as evidence for its documented results (V15–V23). These previously existed only on one local disk…
Access
Public
Updated Jul 23, 2026
Repo size
168 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt168 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026
- SHA
- 8c11ca42
Model card
From the Hugging Face model README
3-Adic Hyperbolic VAE — Canonical Checkpoint Archive
Archives the training-run checkpoints that CLAUDE.md in the source repo
(https://github.com/gesttaltt/3-adic-ml) cites as evidence for its documented
results (V15–V23). These previously existed only on one local disk with no
backup — .gitignore in the source repo has referenced a
checkpoint_hub download tool since early on, but that tool was never
actually built. This repo is that archive, added retroactively.
Each folder has checkpoint.pt (best_Q.pt from the run), config.yaml
(exact training config), and results.json where the run produced one.
| Folder | What it is | Cited in CLAUDE.md as |
|---|---|---|
v15.0_long_term_stability/ | 2000-epoch long-horizon stability run | V15.0 completed |
v16.0_human_fine_tuning/ | Fine-tuned on human TP53 codon windows | V16.0 (Human TP53) completed |
v17.0_rosetta_manifold/ | Grand-master run: synthetic + human TP53 + bioactive peptides, single manifold | Phase 17 "Rosetta Manifold" |
v17.1_rosetta_manifold_resume/ | Resume/continuation of the above | Phase 17 resume |
v21.0_clean_run/ | Best checkpoint epoch 230/1000. ARI(prefix-3, v=0)=1.000, Spearman hierarchy=0.8335, Q=1.9755 | "V21.0 Training Results" |
v23.0_algebraic/ | Best checkpoint epoch 210/1000. Adds algebraic structure signal (4-bit signature, Lagrangian dual ascent). Q=1.9698, hierarchy Spearman=0.8335 | "V23.0 Training Results" |
Note: v17.0_rosetta_manifold has no results.json (wasn't saved at the
time of that run) -- config + checkpoint only.
Loading
import torch
ckpt = torch.load("v21.0_clean_run/checkpoint.pt", weights_only=True)
See the source repo's src/models/vae.py (TernaryVAEV6Controllable) for
the model class, and the corresponding config.yaml in each folder for the
exact architecture/training hyperparameters each checkpoint was produced
with.
Related
For the external validation follow-up (does this architecture generalize to real, non-synthetic biological data?), see geestaltt/3-adic-vae-cytochrome-c -- a separate, negative result on real cytochrome c phylogeny.
- License
- mit
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026