Downloads · 30 days
19
27% of all-time downloads
silx-ai/Quasar-230k
Quasar-230k is a machine learning model from silx-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Quasar-230K is a Quasar hybrid-attention model containing approximately 298.31M Quasar-specific branch parameters. These branches received optimizer training and measurably affect model behavior.
Downloads · 30 days
19
27% of all-time downloads
All-time downloads
70
Public
Parameters
16.6B
33.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors33.1 GB · 100%
From the Hugging Face model README
Quasar-230K is a Quasar hybrid-attention model containing approximately 298.31M Quasar-specific branch parameters. These branches received optimizer training and measurably affect model behavior.
The model’s experts, routers, and Quasar-specific tensors were modified, producing material changes to its stored weights and behavior.