Ajay’s notes

Spacy 101

Notes from https://spacy.io/usage/spacy-101
Sep 6, 2024
1 min

Local LLM Inference on Mac Mini

I have a Mac Mini (16 GB, M1) running in my home network. I am exploring options available to run LLMs on it, so that it does not slow down my work laptop (which is a…
Aug 20, 2024
2 min

LLM Leaderboards and benchmarks

LLMs
Important leaderboards I came across
Aug 20, 2024
6 min

Paper Summary: COT Prompting Elicits Reasoning in Large Language Models

Paper - https://arxiv.org/abs/2201.11903
Aug 12, 2024
2 min

Finding Urban Locality data for India

There was a need to move away from Google Maps for locality data in India due to increase in Google Maps geocoding pricing. We could find very good Village data from Local…
Jul 14, 2024
2 min

Open Street Maps for Geocoding locally

We have a need to geocode (get latlong from an address component) a large number of addresses. Doing it using google maps api would be expensive. Hence trying out Open…
Jun 28, 2024
1 min

Object Detction Finetuning

I was trying to finetune a object detection model on a custom dataset. I was looking for example code for the same, but most examples I could find were for classification.…
May 27, 2024
2 min

Exploring Dspy - part 1

I have a read a lot about the capabilites of the dspy library from stanford. I am trying to understand its various capabilities. Let start with the…
May 27, 2024
7 min

Run Trilium server in google cloud run

Trilium can be used as a personal knowledge base. It can be run locally or synchronized across multiple devices as a server. By using google cloud run as the server, we can…
May 4, 2024
1 min

Run Qdrant in Google Cloud Run

I want to minimize the cost involved in running a Qdrant vector database on Google Cloud.
Feb 12, 2024
1 min

Purpose

We will attempt to understand the ResdSQL paper and its implementation in github
Apr 19, 2023
3 min

This is notes from the ZeRO - Memory Optimization paper
Feb 19, 2023
4 min

Results

Here I am exploring the capabiliteis of Text to SQL of OpenAI codex vs fine-tuned t5-3b model (picard).
Feb 15, 2023
13 min

5 The datasets library

Repeating steps from https://huggingface.co/course/chapter3/4?fw=pt
Jan 30, 2023
1 min

1. Transformer Models

In encoder models, attention layers can access all words in the input sequence. Pretraining involves corruping an input sequence and predicting the original sequence (say…
Jan 23, 2023
2 min 

from transformers import AutoModelForTokenClassification, AutoProcessor
from datasets import ClassLabel, Features, Sequence, Value, Array2D, Array3D, load_metric
import torch…
Nov 1, 2022
1 min

Transformers from scratch in pytorch

Notes from https://uvadlc-notebooks.readthedocs.io/en/latest/tutorial_notebooks/tutorial6/Transformers_and_MHAttention.html
Oct 25, 2022
2 min

Properties of Eigen Values and Vectors

We initialize a random vector x, usually 1s. We multiply ax and divide the output to make the
Jun 29, 2022
1 min

We will try to understand a quantile plot.
Jun 26, 2022
1 min

Passenger dataset

can be downloaded from https://www.kaggle.com/datasets/chirag19/air-passengers
May 13, 2022
1 min

Satender Product Recommendation

From SVD to Deep Learning
Mar 7, 2022
2 min

Movie Recommender using pytorch

Simple implementation
Jan 16, 2022
1 min

Sklearn - Adult Income Classificat

Basics
Jan 10, 2022
1 min

Linear Regression

Basics
Jan 6, 2022
1 min

Variational Inference

Under the hood
Dec 28, 2021
3 min

MIT 18.065 Linear Algebra, Lecture 1

Understanding column spaces
Dec 23, 2021
1 min

sklearn intro

fastpages
jupyter
Classification, Clustering and Regression
Nov 28, 2021
1 min

Hands - on ML. Chapter 1

Classification, Clustering and Regression
Nov 22, 2021
1 min

Fastai Linear Algebra - chapter 1

Image background removal with SGD
Nov 11, 2021
1 min
No matching items