Downloads · 30 days
3
5% of all-time downloads
cas-smo-v33
tope1129/cas-smo-v33
cas-smo-v33 is a machine learning model from tope1129. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fork of garuda-labs/gen-04f5171856b6 aimed at more training series per wall-clock hour.
All-time downloads
59
Public
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py61.4 KB · 92%
At a glance
- Access
- Public
- Created
- Aug 13, 2026
- Updated
- Aug 13, 2026
- SHA
- 31578696
Model card
From the Hugging Face model README
cas-smo-v32
Fork of garuda-labs/gen-04f5171856b6 aimed at more training series per
wall-clock hour.
The parent always emits length 4096. Under stream_cpu the trainer stops
at a fixed token budget, so mean length sets how many series fit in one hour.
Pool 2026-08-09-block-8805600 has mean length ≈1552 (p25=512, p90≈4057).
| Knob | Parent | cas-smo-v32 |
|---|---|---|
p00 (min length) | 4096 | 512 |
p01 (max length) | 4096 | 4096 |
p02 (prefetch) | 2 | 4 |
| Expected mean L | 4096 | ~2304 |
| Series / token-hour | 1× | ~1.8× |
Also: each generate batch builds at the batch max length (not always p01),
so short draws cost less CPU and starve the GPU less.
Family mix / recipes unchanged from the parent. Confirm with:
cascade score ./cas-smo-v32 --pool-dir ./dataset/snapshots/2026-08-09-block-8805600 --train-hours 1 --device cuda
- Created
- Aug 13, 2026
- Updated
- Aug 13, 2026