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
hematteo
/
readout-recipe-control
Like
0
pythia
gpt-neox
pretraining
mech-interp
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
readout-recipe-control
/
warmup_long
976 MB
Ctrl+K
Ctrl+K
2 contributors
History:
1 commit
hematteo
Replace the step-512 pilot pull with the complete 10B-token production runs (5 arms, 16 checkpoints each)
de52470
verified
about 1 month ago
ckpts
Replace the step-512 pilot pull with the complete 10B-token production runs (5 arms, 16 checkpoints each)
about 1 month ago
COMPLETE
11 Bytes
Replace the step-512 pilot pull with the complete 10B-token production runs (5 arms, 16 checkpoints each)
about 1 month ago
config.json
588 Bytes
Replace the step-512 pilot pull with the complete 10B-token production runs (5 arms, 16 checkpoints each)
about 1 month ago
metrics.csv
1.64 kB
Replace the step-512 pilot pull with the complete 10B-token production runs (5 arms, 16 checkpoints each)
about 1 month ago
