 oobabooga
|
e2da6b9685
Fix You You You appearing in chat mode
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
bcf0075278
Merge pull request #235 from xanthousm/Quality_of_life-main
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
3437de686c
Merge pull request #189 from oobabooga/new-streaming
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
341e135036
Various fixes in chat mode
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
b0e8cb8c88
Various fixes in chat mode
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
0bd5430988
Use 'with' statement to better handle streaming memory
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
37f0166b2d
Fix memory leak in new streaming (second attempt)
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
92fe947721
Merge branch 'main' into new-streaming
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
195e99d0b6
Add llama_prompts extension
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
501afbc234
Add requests to requirements.txt
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
2743dd736a
Add *Is typing...* to impersonate as well
|
%!s(int64=2) %!d(string=hai) anos |
 Xan
|
96c51973f9
--auto-launch and "Is typing..."
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
026d60bd34
Remove default preset that didn't do anything
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
e01da4097c
Merge pull request #210 from rohvani/pt-path-changes
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
e9dbdafb14
Merge branch 'main' into pt-path-changes
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
706a03b2cb
Minor changes
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
de7dd8b6aa
Add comments
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
113b791aa5
Merge pull request #219 from deepdiffuser/4bit-multigpu
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
e461c0b7a0
Move the import to the top
|
%!s(int64=2) %!d(string=hai) anos |
 deepdiffuser
|
9fbd60bf22
add no_split_module_classes to prevent tensor split error
|
%!s(int64=2) %!d(string=hai) anos |
|
deepdiffuser
|
ab47044459
add multi-gpu support for 4bit gptq LLaMA
|
%!s(int64=2) %!d(string=hai) anos |
 rohvani
|
2ac2913747
fix reference issue
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
1d7e893fa1
Merge pull request #211 from zoidbb/add-tokenizer-to-hf-downloads
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
875847bf88
Consider tokenizer a type of text
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
8ed214001d
Merge branch 'main' of github.com:oobabooga/text-generation-webui
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
249c268176
Fix the download script for long lists of files on HF
|
%!s(int64=2) %!d(string=hai) anos |
 Ber Zoidberg
|
ec3de0495c
download tokenizer when present
|
%!s(int64=2) %!d(string=hai) anos |
|
rohvani
|
5ee376c580
add LLaMA preset
|
%!s(int64=2) %!d(string=hai) anos |
|
rohvani
|
826e297b0e
add llama-65b-4bit support & multiple pt paths
|
%!s(int64=2) %!d(string=hai) anos |
|
oobabooga
|
7c3d1b43c1
Merge pull request #204 from MichealC0/patch-1
|
%!s(int64=2) %!d(string=hai) anos |
