dangermouse77 commited on
Commit
a79ae95
·
verified ·
1 Parent(s): e952e7c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -4
README.md CHANGED
@@ -2,12 +2,11 @@
2
  license: apache-2.0
3
  ---
4
  A simple script in python to let two GPT4all models talk together about Universe and Life.
 
5
 
6
  The GPT4all models runs on hosts with "Enable API" set to true, and SSH tunnels make sure they are reachable.
7
-
8
  Conversation sentences are stored in a PostgreSQL database with pgvector, and the sentences are embedded with "all-MiniLM-L6-v2" on a 384-dimensional space for later retrieval.
9
 
10
- The code was created with Vibe Programming with help of ChatGPT 4.5.
11
-
12
  For the sample in conversation table, a human introduced the topic with "Measure the Universe", then the debate went on with "Reasoner v1" questioning on a RTX 3050 and "bartowski/gemma-2-9B-it-GGUF" answering on a RTX 3090.
13
- One of the two models is simply instructed to generate a follow up question for the answer of the other model.
 
 
2
  license: apache-2.0
3
  ---
4
  A simple script in python to let two GPT4all models talk together about Universe and Life.
5
+ One of the two models is simply instructed to generate a follow up question for the answer of the other model, after a human introduce some initial topic.
6
 
7
  The GPT4all models runs on hosts with "Enable API" set to true, and SSH tunnels make sure they are reachable.
 
8
  Conversation sentences are stored in a PostgreSQL database with pgvector, and the sentences are embedded with "all-MiniLM-L6-v2" on a 384-dimensional space for later retrieval.
9
 
 
 
10
  For the sample in conversation table, a human introduced the topic with "Measure the Universe", then the debate went on with "Reasoner v1" questioning on a RTX 3050 and "bartowski/gemma-2-9B-it-GGUF" answering on a RTX 3090.
11
+
12
+ The code was created with Vibe Programming with help of ChatGPT 4.5.