Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
0arch-io
/
kisoku-3.2b-base
like
1
Text Generation
mlfoundations/dclm-baseline-1.0-parquet
English
transformer
gpt
maxtext
language-model
causal-lm
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
kisoku-3.2b-base
/
commit_success.txt
0arch-io
Upload Kisoku 3.2B base model (100K steps, loss 2.733)
6f30575
verified
9 days ago
raw
Copy download link
history
blame
contribute
delete
115 Bytes
Checkpoint commit was successful to gs://pantheon-tpu-training/kisoku-checkpoints/kisoku-3.2b-GCS/checkpoints/99999