Rishabh rishabh135

Understanding DSPy: Key Insights and Principles

DSPy represents a significant advancement in the field of AI software development. However, its complexity can make it challenging to fully comprehend. This document aims to clarify the foundational principles of DSPy and outline its core tenets.

Introduction

The central thesis of DSPy is that while large language models (LLMs) and their methodologies will continue to evolve, this progress will not be uniform across all dimensions. Therefore, it is essential to identify:

The minimal set of fundamental abstractions that enable the development of downstream AI software that is "future-proof" and capable of adapting to advancements.

PostgreSQL is Enough

Background and Cron Jobs

Anti-hype LLM reading list

Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.

Foundational Concepts

Pre-Transformer Models

Thoughts and some criticism on "Re-imagining Algorithmic Fairness in India and Beyond".

Yoav Goldberg, Jan 30, 2021

This new paper from Google Research Ethics Team (by Sambasivan, Arnesen, Hutchinson, Doshi, and Prabhakaran) touches on a very imortant topic: research (and supposedly also applied) work on algorithmic fairness---and more broadly AI-ethics---is US-centric[*], reflecting US subgroups, values, and methods. But AI is also applied elsewhere (for example, India). Do the methods and result developed for/in the US transfer? The answer is, of course, no, and the paper is doing a good job of showing it. If you are the kind of person who is impressed by the number of citations, this one has 220, a much higher number than another paper (not) from Google Research that became popular recently and which boasts many citations. I think this current paper (let's call it "the India Paper") is substantially more important, given that it raises a very serious issue that

	# train_grpo.py
	#
	# See https://github.com/willccbb/verifiers for ongoing developments
	#
	"""
	citation:

	@misc{brown2025grpodemo,
	title={Granular Format Rewards for Eliciting Mathematical Reasoning Capabilities in Small Language Models},
	author={Brown, William},

	import argparse
	import random
	import sys

	from transformers import AutoModelForCausalLM, AutoTokenizer, DynamicCache
	import torch

	parser = argparse.ArgumentParser()
	parser.add_argument("question", type=str)
	parser.add_argument(

	# Based on tutorial from https://jeffbradberry.com/posts/2015/09/intro-to-monte-carlo-tree-search/
	# Author: Kyle Kastner
	# License: BSD 3-Clause
	from __future__ import print_function
	import random
	import copy
	import numpy as np
	import time
	import argparse
	import sys

	## Weight norm is now added to pytorch as a pre-hook, so use that instead :)

	import torch
	import torch.nn as nn
	from torch.nn import Parameter
	from functools import wraps

	class WeightNorm(nn.Module):
	append_g = '_g'
	append_v = '_v'

	"""Simple example on how to log scalars and images to tensorboard without tensor ops.

	License: BSD License 2.0
	"""
	__author__ = "Michael Gygli"

	import tensorflow as tf
	from StringIO import StringIO
	import matplotlib.pyplot as plt
	import numpy as np

	def sample_gumbel(shape, eps=1e-20):
	"""Sample from Gumbel(0, 1)"""
	U = tf.random_uniform(shape,minval=0,maxval=1)
	return -tf.log(-tf.log(U + eps) + eps)

	def gumbel_softmax_sample(logits, temperature):
	""" Draw a sample from the Gumbel-Softmax distribution"""
	y = logits + sample_gumbel(tf.shape(logits))
	return tf.nn.softmax( y / temperature)