Downloads · 30 days
0
Yujivus/revolver-120m
revolver-120m is a machine learning model from Yujivus. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for custom. The card lists the license as cc-by-nc-4.0.
Revolver-120M is a 125,829,354-parameter nanochat base model pretrained in a globally base-6 numeral world. Every maximal ASCII decimal digit run in the paired base-10 corpus was rendered in base 6 while document orde…
Downloads · 30 days
0
Access
Public
Updated Aug 15, 2026
Repo size
7.3 GB
Likes
0
Public
Click a slice to open those files.
.pt7.2 GB · 100%
From the Hugging Face model README
Revolver-120M is a 125,829,354-parameter nanochat base model pretrained in a globally base-6 numeral world. Every maximal ASCII decimal digit run in the paired base-10 corpus was rendered in base 6 while document order, arithmetic placement, tokenizer, architecture, seed, optimizer, schedule, and training token budget were held fixed.
The name refers both to a six-shooter and to the Fourier phase rotations used in the accompanying mechanistic-interpretability experiments.
92d63d4e8bb4df75c3b71618f31ddde2378b2bcdThe tokenizer is exactly the same 32K digit-level tokenizer used by the paired
base-10 baseline. Tokens 0 through 5 represent base-6 digits. Tokens 6
through 9 remain in the unchanged vocabulary but are not valid base-6 digits.
These are raw nanochat PyTorch checkpoints, not Transformers AutoModel
checkpoints. Reconstruct the model using the pinned nanochat commit above and
place the tokenizer/checkpoint directories under NANOCHAT_BASE_DIR.
The repository includes intermediate and final model checkpoints, optimizer
states, metadata, training logs, tokenizer files, and the exact RunPod scripts.
Evaluation and Fourier/steering outputs can be added by rerunning the uploader
after those artifacts are created under evals/base6-d8-r48-seed42/.
This repository is not affiliated with Karpathy, NVIDIA, or Hugging Face.