rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity

Chat Mode Improvements

Browse Source 
This commit decouples single line mode, well behaved models no longer need this since we stop at the You:.

There are scenario's however where this potentially breaks chatmode completely or makes models more frustrating to use. Users who experience this can enable the Single Line mode in the formatting menu to restore the old behavior.

I have also allowed token streaming again, since the issues with it have already been resolved.
This commit is contained in:
Henk
2023-01-11 21:33:25 +01:00
parent 9e1bab9575
commit 271e4ed06b
1 changed files with 1 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
aiserver.py
View File

@@ -2474,9 +2474,6 @@ def patch_transformers():
if not koboldai_vars.output_streaming:
return False
if koboldai_vars.chatmode:
return False
data = [applyoutputformatting(utils.decodenewlines(tokenizer.decode(x[-1])), no_sentence_trimming=True, no_single_line=True) for x in input_ids]
koboldai_vars.actions.stream_tokens(data)
@@ -6507,7 +6504,7 @@ def applyoutputformatting(txt, no_sentence_trimming=False, no_single_line=False)
if(koboldai_vars.frmtrmspch):
txt = utils.removespecialchars(txt, koboldai_vars)
# Single Line Mode
if((koboldai_vars.singleline or koboldai_vars.chatmode) and not no_single_line):
if(koboldai_vars.singleline and not no_single_line):
txt = utils.singlelineprocessing(txt, koboldai_vars)
for sub in koboldai_vars.substitutions: