- Create a new directory with these three files (requirements.txt, main.py, README.md)
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python main.py
- Update
main()
to run the example prompt chains
Discover gists
#!/usr/bin/env python3 | |
import sys | |
import json | |
import os | |
def find_account_inclusion_object(eligibles, eth_address): | |
for account in eligibles: | |
if account["identity"].lower() == eth_address.lower(): | |
return account | |
return None |
13911.1 swader | |
13911.1 sorpaas | |
13911.1 s1na | |
13911.1 rjl493456442 | |
13911.1 qd-qd | |
13911.1 protolambda | |
13911.1 paulrberg | |
13911.1 noahzinsmeister | |
13911.1 neurone |
Code is clean if it can be understood easily – by everyone on the team. Clean code can be read and enhanced by a developer other than its original author. With understandability comes readability, changeability, extensibility and maintainability.
- Follow standard conventions.
- Keep it simple stupid. Simpler is always better. Reduce complexity as much as possible.
- Boy scout rule. Leave the campground cleaner than you found it.
- Always find root cause. Always look for the root cause of a problem.
######################################################################## | |
# OPTIMAL .htaccess FILE FOR SPEED AND SECURITY @Version 2.0.9 - 03/2024 | |
# ---------------------------------------------------------------------- | |
# @Author: Andreas Hecht | |
# @Author URI: https://seoagentur-hamburg.com | |
# License: GNU General Public License v2 or later | |
# License URI: http://www.gnu.org/licenses/gpl-2.0.html | |
######################################################################## | |
Ref : stackoverflow
The best solution in my opinion is to use the unittest
[command line interface][1] which will add the directory to the sys.path
so you don't have to (done in the TestLoader
class).
For example for a directory structure like this:
new_project
├── antigravity.py
Good question! I am collecting human data on how quantization affects outputs. See here for more information: ggerganov/llama.cpp#5962
In the meantime, use the largest that fully fits in your GPU. If you can comfortably fit Q4_K_S, try using a model with more parameters.
See the wiki upstream: https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix
import autogen | |
from user_proxy_webagent import UserProxyWebAgent | |
import asyncio | |
config_list = [ | |
{ | |
"model": "gpt-3.5-turbo", | |
# "api_key": "<YOUR KEY HERE>" | |
} | |
] |