vgel

system: |
  Assistant is acting as a helpful reference. The user is asking the given question through a command line interface and needs a concise answer. The interface does not support markdown, so the response should be plaintext. The response should be as concise as possible while still answering the question. For example, if the question is about the appropriate command to perform an action, the response should be just the command and nothing else. If the question is about a Python feature, the response should be just a code snippet, perhaps with a single-line explanatory comment if necessary--but assume the user is an expert and will ask clarifying questions if needed.
  
  # Examples
  
  Human: how do i write a for-loop in bash?
  Assistant: $bash_command
  
  Human: python mro lookup order
  Assistant: # depth first, then left to right

vgel

import json

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

from repeng import ControlVector, ControlModel, DatasetEntry

model_name = "mistralai/Mistral-7B-Instruct-v0.1"

tokenizer = AutoTokenizer.from_pretrained(model_name)

vgel

[
  {
    "model": "34m",
    "index": 6426,
    "desc": "Grove startup; Gateway cloning technology",
    "usable": true
  },
  {
    "model": "34m",
    "index": 19443,

vgel

Play this game by pasting the script in http://www.puzzlescript.net/editor.html

vgel

Play this game by pasting the script in http://www.puzzlescript.net/editor.html

vgel

Play this game by pasting the script in http://www.puzzlescript.net/editor.html

vgel

import os

import tqdm
import openai

openai.api_key = os.environ["OPENAI_API_KEY"]


def get_response(usermsg):
    response = openai.ChatCompletion.create(

vgel

# pip install beautifulsoup4 requests markdownify mistletoe

# command line usage: python chunkpaper.py 'https://ar5iv.org/abs/1910.06709'
# will dump the HTML, Markdown, and finally the chunk JSON
# note that (as of Nov 8 '23) ar5iv only has arxiv papers converted up to the end of October,
# but if you need something more recent you could probably do the LaTeX→HTML conversion yourself

# library usage: call `chunk` with some ar5iv HTML. will probably choke on anything else

import dataclasses

vgel

Bantu Lexical Reconstructions 3

→ Browseable version with Datasette

Extracted from BLR, via their Filemaker database download.

vgel

# put in rss_proxy/ as app.py and run with `python -m flask run`
# requirements: flask beautifulsoup4 requests lxml
# usage: `curl localhost:5000?feed=https://instance.example.com/users/username.rss`

from bs4 import BeautifulSoup
from flask import Flask, request
import requests
from lxml.builder import E
import lxml.etree