scriptos/ollamarama-matrix-chatbot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

switched model to a more efficient quantization level

Browse Source
This commit is contained in:
Dustin 2023-12-17 14:31:29 -05:00
parent 52837bd024
commit 58e15ca543
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
ollamarama.py
View File

@ -30,7 +30,7 @@ class ollamarama:
self.prompt = ("you are ", ". speak in the first person and never break character.") self.prompt = ("you are ", ". speak in the first person and never break character.")
#set model, this one works best in my tests with the hardware i have, but you can try others #set model, this one works best in my tests with the hardware i have, but you can try others
self.model = "ollama/zephyr:7b-beta-q8_0" self.model = "ollama/zephyr:7b-beta-q6_K"
# get the display name for a user # get the display name for a user
@ -111,7 +111,7 @@ class ollamarama:
except Exception as e: except Exception as e:
print(e) print(e)
#Shrink history list for token size management #Shrink history list for token size management
if len(self.messages[channel][sender]) > 20: if len(self.messages[channel][sender]) > 30:
del self.messages[channel][sender][1:3] #delete the first set of question and answers del self.messages[channel][sender][1:3] #delete the first set of question and answers
# change the personality of the bot # change the personality of the bot