gachzhan's starred repositories

ThunderKittens

Tile primitives for speedy kernels

Language:CudaLicense:MITStargazers:1260Issues:0Issues:0

nlp_course

YSDA course in Natural Language Processing

Language:Jupyter NotebookLicense:MITStargazers:9513Issues:0Issues:0

example-code-2e

Example code for Fluent Python, 2nd edition (O'Reilly 2022)

Language:PythonLicense:MITStargazers:3016Issues:0Issues:0

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Language:PythonLicense:Apache-2.0Stargazers:1877Issues:0Issues:0

scenic

Scenic: A Jax Library for Computer Vision Research and Beyond

Language:PythonLicense:Apache-2.0Stargazers:3075Issues:0Issues:0

The-Art-of-Linear-Algebra

Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"

Language:PostScriptLicense:CC0-1.0Stargazers:15183Issues:0Issues:0

knn-ood

Code for ICML 2022 paper "Out-of-distribution Detection with Deep Nearest Neighbors"

Language:PythonStargazers:164Issues:0Issues:0

Tools-to-Design-or-Visualize-Architecture-of-Neural-Network

Tools to Design or Visualize Architecture of Neural Network

Stargazers:4182Issues:0Issues:0
Language:Jupyter NotebookLicense:MITStargazers:140Issues:0Issues:0

jaxton

100 exercises to learn JAX

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:556Issues:0Issues:0

computer-science

:mortar_board: Path to a free self-taught education in Computer Science!

License:MITStargazers:164638Issues:0Issues:0

tabular-transfer-learning

A repo for transfer learning with deep tabular models

Language:PythonLicense:MITStargazers:99Issues:0Issues:0

tokengt

[NeurIPS'22] Tokenized Graph Transformer (TokenGT), in PyTorch

Language:PythonLicense:MITStargazers:306Issues:0Issues:0

spinningup

An educational resource to help anyone learn deep reinforcement learning.

Language:PythonLicense:MITStargazers:9750Issues:0Issues:0

professional-programming

A collection of learning resources for curious software engineers

Language:PythonLicense:MITStargazers:45673Issues:0Issues:0

FreTS

Official implementation of the paper "Frequency-domain MLPs are More Effective Learners in Time Series Forecasting"

Language:PythonLicense:Apache-2.0Stargazers:101Issues:0Issues:0

fine-tune-mistral

Fine-tune mistral-7B on 3090s, a100s, h100s

Language:PythonLicense:MITStargazers:689Issues:0Issues:0

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Language:PythonLicense:BSD-3-ClauseStargazers:5265Issues:0Issues:0

SemDeDup

Code for "SemDeDup", a simple method for identifying and removing semantic duplicates from a dataset (data pairs which are semantically similar, but not exactly identical).

Language:PythonLicense:NOASSERTIONStargazers:74Issues:0Issues:0

generative-ai-for-beginners

18 Lessons, Get Started Building with Generative AI 🔗 https://microsoft.github.io/generative-ai-for-beginners/

Language:Jupyter NotebookLicense:MITStargazers:46794Issues:0Issues:0

kubernetes-the-hard-way

Bootstrap Kubernetes the hard way. No scripts.

License:Apache-2.0Stargazers:39396Issues:0Issues:0

ml-engineering

Machine Learning Engineering Open Book

Language:PythonLicense:CC-BY-SA-4.0Stargazers:10054Issues:0Issues:0

iTransformer

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

Language:PythonLicense:MITStargazers:359Issues:0Issues:0

instagraph

Converts text input or URL into knowledge graph and displays

Language:PythonLicense:MITStargazers:3224Issues:0Issues:0

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Language:PythonLicense:BSD-4-ClauseStargazers:9625Issues:0Issues:0

wal-e

Continuous Archiving for Postgres

Language:PythonLicense:BSD-3-ClauseStargazers:3433Issues:0Issues:0

polars

Dataframes powered by a multithreaded, vectorized query engine, written in Rust

Language:RustLicense:NOASSERTIONStargazers:27030Issues:0Issues:0

wasm4-raycaster

A demo raycaster for the WASM-4 engine.

Language:HTMLLicense:MITStargazers:89Issues:0Issues:0

lance

Modern columnar data format for ML and LLMs implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..

Language:RustLicense:Apache-2.0Stargazers:3413Issues:0Issues:0

Sophia

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Language:PythonLicense:Apache-2.0Stargazers:367Issues:0Issues:0