tanaymeh

aim

Aim 💫 — An easy-to-use & supercharged open-source experiment tracker.

ml-engineering

Machine Learning Engineering Open Book

manim

Animation engine for explanatory math videos

min-fsdp

ragas

Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines

install-guides

Various installation guides for Large Language Models

leetcode-solutions

My solutions to Leetcode Problems

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

LeetCode-Questions-CompanyWise

Contains Company Wise Questions sorted based on Frequency and all time

lm-evaluation-harness

A framework for few-shot evaluation of language models.

NeMo-Skills

A pipeline to improve skills of large language models

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

LLM101n

LLM101n: Let's build a Storyteller

llm-mcts

[NeurIPS 2023] We use large language models as commonsense world model and heuristic policy within Monte-Carlo Tree Search, enabling better-reasoned decision-making for daily task planning problems.

distillm

Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)

clip-training

Code to train CLIP model

CodeInstruct

InstructCoder (former name:Codelnstruct) enables LLMs to edit code

GPTeacher

A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

distilling-step-by-step

evaluation-pipeline-2024

The evaluation pipeline for the 2024 BabyLM Challenge.

simpleautodiff

A simple implementation of automatic differentiation.

fms-fsdp

🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash attention v2.

WeightWatcher

The WeightWatcher tool for predicting the accuracy of Deep Neural Networks

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Hands-on-Reinforcement-Learning-with-PyTorch

Hands-on Reinforcement Learning with PyTorch, published by [Packt]

TD3

Author's PyTorch implementation of TD3 for OpenAI gym tasks

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

flappy-bird-gym

An OpenAI Gym environment for the Flappy Bird game

flappy-bird-gymnasium

An OpenAI Gym environment for the Flappy Bird game