Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
farguney
/
trident
like
0
Safetensors
trident-arch
byte-level
recurrent
variable-rate
cpu-inference
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
trident
/
src
Ctrl+K
Ctrl+K
1 contributor
History:
21 commits
farguney
refiner: ReZero gates (a_attn/a_ffn init 0) -> identity at init, stable deep weight-shared iteration (fixes eval-BPB divergence)
992c1e0
verified
24 minutes ago
trident
refiner: ReZero gates (a_attn/a_ffn init 0) -> identity at init, stable deep weight-shared iteration (fixes eval-BPB divergence)
24 minutes ago
