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
kevinindustries
/
kevin-chat
like
0
Follow
Kevin Industries
2
transformer
from-scratch
decoder-only
cuda
pytorch-free
chat
sft
License:
mit
Model card
Files
Files and versions
xet
Community
5
Copy to bucket
new
main
kevin-chat
Ctrl+K
Ctrl+K
1 contributor
History:
8 commits
pstaykov
Document EOS-token SFT change and known overfitting/turn-ending limitations
87ddfe1
verified
2 days ago
tokenizer
Add tokenizer/tokenizer.bbpe (#2)
3 days ago
.gitattributes
Safe
1.58 kB
Add tokenizer/tokenizer.bbpe (#2)
3 days ago
README.md
5.6 kB
Document EOS-token SFT change and known overfitting/turn-ending limitations
2 days ago
latest.ckpt
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
332 MB
xet
Update chat checkpoint to step 162000 (EOS-token SFT, repetition-penalty inference support)
2 days ago