Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mariochampion/gpt3-robo-writingpartner
https://github.com/mariochampion/gpt3-robo-writingpartner
Last synced: about 1 month ago
JSON representation
- Host: GitHub
- URL: https://github.com/mariochampion/gpt3-robo-writingpartner
- Owner: mariochampion
- License: mit
- Created: 2021-01-03T17:15:37.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2021-01-12T03:15:34.000Z (about 4 years ago)
- Last Synced: 2024-10-30T07:57:47.540Z (3 months ago)
- Language: Python
- Size: 12.7 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# gpt3-robo-writingpartner
Initial Commit -- instructions to come**Intention**
On the way to understanding how to get code creation out of GPT-3, it seems worth while to play with it in various capacities.
And this capacity is the idea generation element, tweaking the `temperature`, `top-p`, `response length`, `frequency penalty` and of course the engine.(much more to come!)
**Requires**
1. Python installed
-- This script uses Python 3, and so i didnt test Python 2.7 (which ships with macOS)
2. An OpenAI API key
-- If you don't have one, you can request one at https://beta.openai.com
3. Know how to add and export environment variables to your bash_profile, so you do not put your APIKEY in source control
-- https://www.schrodinger.com/kb/1842
-- quick example of what i added to my bash_profile
`# openai vars`
`export OPENAI_API_KEY=""`**ToDos**
# append to `.log` so one json object with many entries
# in gpt3.py use configured or passed param values
# create interactive or run-time passed args for temp, top-p, freq, etc