Hankcs
hankcs
AI & ML interests
None yet
Recent Activity
new activity
about 2 months ago
answerdotai/ModernBERT-large:Why add_prefix_space=false?
new activity
4 months ago
LLM360/TxT360:Comparison with DCLM-baseline
liked
a dataset
5 months ago
jetaudio/zh_novels
Organizations
None yet
hankcs's activity
Why add_prefix_space=false?
#5 opened about 2 months ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Comparison with DCLM-baseline
2
#1 opened 4 months ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Choice of positional encodings?
2
#17 opened over 1 year ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Is the 7B trained on 1.5 trillion tokens, but the *40B* on 1 trillion only?
3
#10 opened over 1 year ago
by
alpindale
![](https://cdn-avatars.huggingface.co/v1/production/uploads/635567189c72a7e742f1419c/tbfBz0furS-y4ISgoe6j0.jpeg)
Data Integrity Checksums
3
#2 opened almost 2 years ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Is there a code generation demo?
4
#17 opened about 2 years ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Is there a code generation demo?
4
#17 opened about 2 years ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)
Is there a code generation demo?
4
#17 opened about 2 years ago
by
hankcs
![](https://cdn-avatars.huggingface.co/v1/production/uploads/1659043660560-62e2fefda63b58b8eb738cff.jpeg)