A looped transformer that rivals much larger models. However, due to the looping, it is rather slow, which calls into question its utility compared with a larger model.
Specs
Params4B total (3B non-embedding)
LicenseApache-2.0
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.05×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
34K
last 30d
76.5K
all time
HF Likes
749
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
