 oobabooga
|
7b1b1d8e39
Make the code more like PEP8
|
%!s(int64=2) %!d(string=hai) anos |
 SDS
|
378d21e80c
Add LLaMA-Precise preset (#767)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
e722c240af
Add Instruct mode
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
65d8a24a6d
Show profile pictures in the Character tab
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
b24147c7ca
Document --pre_layer
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
4c9ed09270
Update settings template
|
%!s(int64=2) %!d(string=hai) anos |
 OWKenobi
|
dcf61a8897
"character greeting" displayed and editable on the fly (#743)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
b0890a7925
Add shared.is_chat() function
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
b857f4655b
Update shared.py
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
2c52310642
Add --threads flag for llama.cpp
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
1d1d9e40cd
Add seed to settings
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
d4a9b5ea97
Remove redundant preset (see the plot in #587)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
55755e27b9
Don't hardcode prompts in the settings dict/json
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
1cb9246160
Adapt to the new model names
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
010b259dde
Update documentation
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
036163a751
Change description
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
005f552ea3
Some simplifications
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
fde92048af
Merge branch 'main' into catalpaaa-lora-and-model-dir
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
49c10c5570
Add support for the latest GPTQ models with group-size (#530)
|
%!s(int64=2) %!d(string=hai) anos |
 catalpaaa
|
b37c54edcf
lora-dir, model-dir and login auth
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
c5ebcc5f7e
Change the default names (#518)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
7618f3fe8c
Add -gptq-preload for 4-bit offloading (#460)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
ddb62470e9
--no-cache and --gpu-memory in MiB for fine VRAM control
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
a78b6508fc
Make custom LoRAs work by default #385
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
c753261338
Disable stop_at_newline by default
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
29fe7b1c74
Remove LoRA tab, move it into the Parameters menu
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
214dc6868e
Several QoL changes related to LoRA
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
104293f411
Add LoRA support
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
4d64a57092
Add Interface mode tab
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
265ba384b7
Rename a file, add deprecation warning for --load-in-4bit
|
%!s(int64=2) %!d(string=hai) anos |
