 oobabooga
|
c2a863f87d
Mention the updated one-click installer
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
1edfb96778
Fix loading extensions from within the interface
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
304f812c63
Gracefully handle CUDA out of memory errors with streaming
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
b2f356a9ae
Generalize GPTQ_loader, support any model (#615 from mayaeary/feature/gpt-j-4bit-v2)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
010b259dde
Update documentation
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
0bec15ebcd
Reorder imports
|
%!s(int64=2) %!d(string=hai) anos |
 Maya Eary
|
41ec682834
Disable kernel threshold for gpt-j
|
%!s(int64=2) %!d(string=hai) anos |
 Maya
|
1ac003d41c
Merge branch 'oobabooga:main' into feature/gpt-j-4bit-v2
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
aebd3cf110
Merge pull request #616 from mayaeary/fix/api-convert-params
|
%!s(int64=2) %!d(string=hai) anos |
|
Maya Eary
|
d1377c37af
Fixes for api server - chat mode and integer temperature
|
%!s(int64=2) %!d(string=hai) anos |
|
Maya Eary
|
1c075d8d21
Fix typo
|
%!s(int64=2) %!d(string=hai) anos |
|
Maya Eary
|
c8207d474f
Generalized load_quantized
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
cac577d99f
Fix interface reloading
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
88ad86249d
Remove unnecessary file
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
91aa5b460e
If both .pt and .safetensors are present, download only safetensors
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
8579fe51dd
Fix new lines in the HTML tab
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
46f6536fae
Merge pull request #570 from mcmonkey4eva/add-train-lora-tab
|
%!s(int64=2) %!d(string=hai) anos |
 Alex "mcmonkey" Goodwin
|
b0f05046b3
remove duplicate import
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
e817fac542
better defaults
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
9cc811a0e6
fix LoRA path typo in #549
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
2e08af4edf
implement initial Raw Text File Input
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
b749952fe3
change number minimums to 0
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
ec6224f556
use new shared.args.lora_dir
|
%!s(int64=2) %!d(string=hai) anos |
|
Alex "mcmonkey" Goodwin
|
31f04dc615
Merge branch 'main' into add-train-lora-tab
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
966168bd2a
Merge pull request #602 from oobabooga/dependabot/pip/accelerate-0.18.0
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
c188975a01
Merge pull request #549 from catalpaaa/lora-and-model-dir
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
53da672315
Fix FlexGen
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
ee95e55df6
Fix RWKV tokenizer
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
036163a751
Change description
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
30585b3e71
Update README
|
%!s(int64=2) %!d(string=hai) anos |
