| .. |
|
GPTQ_loader.py
|
dcfd866402
Allow loading of .safetensors through GPTQ-for-LLaMa
|
%!s(int64=2) %!d(string=hai) anos |
|
LoRA.py
|
25be9698c7
Fix LoRA on mps
|
%!s(int64=2) %!d(string=hai) anos |
|
RWKV.py
|
4578e88ffd
Stop the bot from talking for you in chat mode
|
%!s(int64=2) %!d(string=hai) anos |
|
callbacks.py
|
8c8e8b4450
Fix the early stopping callback #559
|
%!s(int64=2) %!d(string=hai) anos |
|
chat.py
|
507db0929d
Do not use empty user messages in chat mode
|
%!s(int64=2) %!d(string=hai) anos |
|
deepspeed_parameters.py
|
f38c9bf428
Fix deepspeed (oops)
|
%!s(int64=3) %!d(string=hai) anos |
|
extensions.py
|
8fad84abc2
Update extensions.py
|
%!s(int64=2) %!d(string=hai) anos |
|
html_generator.py
|
6e1b16c2aa
Update html_generator.py
|
%!s(int64=2) %!d(string=hai) anos |
|
models.py
|
a6bf54739c
Revert models.py (accident)
|
%!s(int64=2) %!d(string=hai) anos |
|
shared.py
|
c5ebcc5f7e
Change the default names (#518)
|
%!s(int64=2) %!d(string=hai) anos |
|
text_generation.py
|
b740c5b284
Add display of context when input was generated
|
%!s(int64=2) %!d(string=hai) anos |
|
training.py
|
5c49a0dcd0
fix error from prepare call running twice in a row
|
%!s(int64=2) %!d(string=hai) anos |
|
ui.py
|
d30a14087f
Further reorganize the UI
|
%!s(int64=2) %!d(string=hai) anos |
Alex "mcmonkey" Goodwin
5c49a0dcd0
fix error from prepare call running twice in a row