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
rfi-irfos
/
albert
like
2
Text Generation
Rust
9 languages
albert-moe
mixture-of-experts
ternary-weights
Mixture of Experts
edge-ai
research
candle
federated-learning
low-precision
sprind
dual-stream
cord-surgery
net2net
License:
lgpl-3.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
5cb92d1
albert
63.1 MB
Ctrl+K
Ctrl+K
1 contributor
History:
30 commits
rfi-irfos
add albert v3.0 config (matches best.safetensors)
5cb92d1
verified
about 2 months ago
.gitattributes
Safe
1.59 kB
add albert v3.0 21L ternary weight artifact (.trit, 5-trits/byte packed)
2 months ago
README.md
Safe
17.8 kB
docs: de-stale model card to live state (30L dual-stream, ep~6205, EP-AVG ATL 6.4339 @ ep6132, chip ATL 1.2637, 128ctx, 18 surgeries + cord)
about 2 months ago
albert_v3.0.config.json
Safe
256 Bytes
add albert v3.0 config (matches best.safetensors)
about 2 months ago
albert_v3.0_21L-256H-12E.trit
Safe
60.9 MB
xet
add albert v3.0 21L ternary weight artifact (.trit, 5-trits/byte packed)
2 months ago
config.json
Safe
569 Bytes
update: num_hidden_layers 21->22 (S10 complete)
2 months ago
vocab.json
Safe
2.25 MB
Add vocab.json
3 months ago
