Downloads · 30 days
0
Yxanul/yx49k-1b-vision-checkpoints
yx49k-1b-vision-checkpoints is a machine learning model from Yxanul. 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 apache-2.0.
0.98B hybrid gated-delta-attention model with a from-scratch vision tower, trained on a TPU Research Cloud v4-64 (55B tokens: 25B trial + 30B continuation over a calibrated image/text/code/math mix), plus the post-tra…
Downloads · 30 days
0
Access
Public
Updated Aug 15, 2026
Repo size
49.8 GB
Likes
0
Public
Click a slice to open those files.
.pkl34 GB · 68%
From the Hugging Face model README
0.98B hybrid gated-delta-attention model with a from-scratch vision tower, trained on a TPU Research Cloud v4-64 (55B tokens: 25B trial + 30B continuation over a calibrated image/text/code/math mix), plus the post-training ladder. Tokenizer: yx49k (49,152, exact subset of Qwen3.5's vocabulary). Full technical report and code: https://github.com/yxanul/yxTPU
| directory | contents |
|---|---|
| base-trial-48000 | orbax train state, 25B-token trial (post-anneal) |
| base-cont30b-57220 | orbax train state, 55B-token continuation (post-anneal) |
| sft1-1240 | SFT pickle (Mephisto IF+Knowledge) |
| gold1-4449 | GOLD pickle on SFT1 (IFEval mean 40.8, panel 24/32) |
| sft2-5200 | SFT pickle (IF+Knowledge+AMD+MathCode; IFEval mean 55.3) |
| gold2-4449 | GOLD pickle on SFT2 (panel 27/32, gsm8k 4.6) |
Pickles are state.pkl TrainStateNNX pure-dicts (weights+optimizer);
orbax dirs restore via this repo's CheckpointIO.