tedtieken

SPARC Framework Prompt Template

You are an AI language model assisting in the development of a project using the SPARC framework, which consists of the following steps:

Models	Examples
Display ads	Yahoo!
Search ads	Google

	#!/usr/bin/env python3
	import argparse, json, sys, time
	from urllib import request

	PROMPTS = [
	{"name": "code_python", "prompt": "Write a Python function that returns the n-th Fibonacci number using memoization. Include a docstring."},
	{"name": "code_cpp", "prompt": "Write a C++ template function `clamp(x, lo, hi)` that returns x clamped to [lo, hi]. No std::clamp."},
	{"name": "explain_concept", "prompt": "Explain how speculative decoding works in large language model inference, in three short paragraphs."},
	{"name": "summarize", "prompt": "Summarize in two sentences: The Industrial Revolution began in Britain in the late 18th century, transforming manufacturing through mechanization, steam power, and the factory system. It spread to continental Europe and North America during the 19th century."},
	{"name": "qa_factual", "prompt": "Q: What are the four fundamental forces of physics?\nA:"},

	#!/usr/bin/env python3

	import requests # for getting URL
	import json # for parsing json
	from datetime import datetime # datetime parsing
	import pytz # timezone adjusting
	import csv # for making csv files
	import os

	#################################################################

	#!comment: This allegedly waa a list of "the top 100,000 most frequently-used English words", see the repo I forked for more provenance.
	#!comment: But it was very un-sanitized. I had a specific purpose in mind, and thought it might be somewhat more generally useful to have/share in the future, so here's how I sanitized the list:
	#!comment: 0) put a number on each word (I should note that somehow it only included 98,913 to start with)
	#!comment: 1) change all words to lower-case
	#!comment: 2) blank out any words with characters other than a-z
	#!comment: 3) remove any duplicates, keeping the lower (more frequent) number
	#!comment: Now the list is 62916 words long, and still contains a lot of non-English words, but I think it is more useful.
	#!comment:
	#!comment: Format: Rank (original rank) Word
	1 (1) the