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
Arko007
/
Zenyx-100M-Base
Like
2
Text Generation
PyTorch
Safetensors
English
causal-lm
base-model
from-scratch
muon
gqa
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
Zenyx-100M-Base
34.7 GB
Ctrl+K
Ctrl+K
1 contributor
History:
918 commits
Arko007
prune main-v1 step 18600
e4c7652
verified
4 minutes ago
cache
z100 compile cache
about 15 hours ago
checkpoints
prune main-v1 step 18600
4 minutes ago
data
z100 held-out validation texts
6 days ago
runs
pilot-i-mtp-m02 final fp16
6 days ago
tokenizer_candidates
tokenizer candidate 49152
7 days ago
tokenizer_candidates_v2
tokenizer candidate v2 57344
7 days ago
tokenizer_candidates_v3
duplicate-free rebuild F-57344-f70
6 days ago
wheels
flash-attention-turing interface
6 days ago
.gitattributes
Safe
1.62 kB
flash-attention-turing wheel (torch 2.11.0+cu128)
6 days ago
README.md
20.5 kB
Card: segment memory measured at step 18,670 (passcode ranking 92% at 32k with memory vs 21% without, natural-text gain 0.035 nats, but free generation of the passcode only 0-5%); core benchmarks of step 18,600 added
about 1 hour ago
