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
ChrisMcCormick
/
decoderstack-d24
like
0
English
decoderstack
nanochat
pretraining
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
decoderstack-d24
/
runs
/
fastrl
13.1 MB
Ctrl+K
Ctrl+K
1 contributor
History:
3 commits
ChrisMcCormick
ep1-ppr32: full-epoch stock-algorithm RL โ collapse by r140; rollouts + metrics
c537b95
verified
6 days ago
align10
align10: 10-round aligned chat_rl_fast smoke off the tool-free SFT ckpt (rollouts + metrics)
6 days ago
ep1-ppr32
ep1-ppr32: full-epoch stock-algorithm RL โ collapse by r140; rollouts + metrics
6 days ago
ppr32-scope
ppr32-scope: 60-round single-GPU throughput scope, 512 rollouts/round @ 2.1s
6 days ago