A series of open MoEs by the Chinese Ant Group. The tech report details their approach to training these models, including the mixing of different GPUs (some of which are not NVIDIA).
Specs
Params290B
LicenseMIT
Tags
Adoption · Hugging Face
RAM score
—
Hugging Face Downloads
72
last 30d
1.2K
all time
HF Likes
31
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
