Downloads · 30 days
24
47% of all-time downloads
stefaniancu/rost-73m-en-baseline
rost-73m-en-baseline is a machine learning model from stefaniancu. 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 cc-by-nc-4.0.
73M parameter nanochat GPT (base stage), research tag d6, checkpoint step 001062.
Downloads · 30 days
24
47% of all-time downloads
All-time downloads
51
Public
Repo size
194 MB
Likes
0
Public
Click a slice to open those files.
.pt194 MB · 100%
From the Hugging Face model README
73M parameter nanochat GPT (base stage), research tag d6, checkpoint step 001062.
Part of the rost model zoo — the full set of trained variants behind the rost research series, published for reproducibility. This is a research model, not a product.
| architecture | nanochat GPT, 6 layers, 384 embed, 2048 context |
| tokenizer | included under tokenizer/ (32,768 vocab) |
| training mixture | English only (ClimbMix) |
| stage | base |
| val bpb (own split) | 1.02546 |
The English control model (research tag d6, experiment 000): the same recipe with no Romanian at all, used as the reference point for every bilingual arm.
Validation bits-per-byte is measured on this arm's own validation split and is not comparable across arms — cross-arm comparisons in the rost write-ups are always cross-evaluated on identical text.
CC-BY-NC-4.0, non-commercial, inherited from the most restrictive component of the training data.