add a newline to restart the container, which was stopped due to HF server down
f998e8f
verified
Sebastian
commited on
Commit History
Update app.py
de15f45
verified
Sebastian
commited on
Update app.py
d51d76f
verified
Sebastian
commited on
set max_new_tokens to 50 instead of 30
6ef22f3
verified
Sebastian
commited on
use gpt2-medium instead of gpt2-large
6e0d084
verified
Sebastian
commited on
fix italic font to bold
6d80e45
Saibo Geng
commited on
put on bold up to truncation
2f4db23
Saibo Geng
commited on
better documentation
4d5cbc9
Saibo Geng
commited on
use gpt-large and optimum package for faster cpu infernce
b5b0c27
Saibo Geng
commited on
remove repetition penalty
d7755a4
Saibo Geng
commited on
use a shorter description
075c5ca
Saibo Geng
commited on
Update README.md
f763bed
verified
Sebastian
commited on
use smaller repetition penalty; add doc
a1aa766
Saibo Geng
commited on
instantiate a new grammar object for each call
805081b
Saibo Geng
commited on
fix tokenizer is not fast tokenizer issue
7a24b1b
Saibo Geng
commited on
add json grammar constraint
92dde49
Saibo Geng
commited on
use Gante GPT2 code
5204c67
Saibo Geng
commited on
use GPT2 instead of T5
f026dba
Saibo Geng
commited on