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

Reduced default max_length parameter to 512.

Browse Source 
Added warning about VRAM usage to Max Tokens tooltip.
This commit is contained in:
KoboldAI Dev
2021-05-07 19:04:51 -04:00
parent d632976fbf
commit ba1ba0fc8a
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
aiserver.py
View File

@ -48,7 +48,7 @@ class vars:
model = ""
noai = False # Runs the script without starting up the transformers pipeline
aibusy = False # Stops submissions while the AI is working
max_length = 1024 # Maximum number of tokens to submit per action
max_length = 512 # Maximum number of tokens to submit per action
ikmax = 3000 # Maximum number of characters to submit to InferKit
genamt = 60 # Amount of text for each action to generate
ikgen = 200 # Number of characters for InferKit to generate