Beast code in Giters

Anjan Nepal's starred repositories

hmm

Large-scale unsupervised Hidden Markov Model (HMM) implementation supporting online-learning and multi-threading

Language:Java800

mamba

Mamba SSM architecture

Language:PythonApache-2.01201200

long-range-arena

Long Range Arena for Benchmarking Efficient Transformers

Language:PythonApache-2.070700

netron

Visualizer for neural network, deep learning and machine learning models

Language:JavaScriptMIT2704200

tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

Language:PythonApache-2.0419200

open_llama

OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

Apache-2.0731300

shuttle

Build & ship backends without writing any infrastructure files.

Language:RustApache-2.0583200

prophet

Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.

Language:PythonMIT1813100

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Language:PythonApache-2.01080900

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

Language:PythonApache-2.02922100

h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

Language:PythonApache-2.01108700

splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)

Language:PythonNOASSERTION71900

gpt-engineer

Specify what you want it to build, the AI asks for clarification, and then builds it. Not actively maintained.

Language:PythonMIT5154500

mojo

The Mojo Programming Language

Language:MojoNOASSERTION2248000

tiktoken

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Language:PythonMIT1137400

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Language:PythonMIT3533500

capnproto

Cap'n Proto serialization/RPC system - core tools and C++ library

Language:C++NOASSERTION1144900

are-16-heads-really-better-than-1

Code for the paper "Are Sixteen Heads Really Better than One?"

Language:ShellMIT16300

bort

Repository for the paper "Optimal Subarchitecture Extraction for BERT"

Language:PythonApache-2.046800

batnoter

An open source, markdown-based, self-hosted note taking webapp.

Language:TypeScriptMIT233100

coding-interview-university

A complete computer science study plan to become a software engineer.

CC-BY-SA-4.030118700

xxHash

Extremely fast non-cryptographic hash algorithm

Language:CNOASSERTION881200

snorkel

A system for quickly generating training data with weak supervision

Language:PythonApache-2.0576900

resilience4j

Resilience4j is a fault tolerance library designed for Java8 and functional programming

Language:JavaApache-2.0959900

Systems design is the process of defining the architecture, modules, interfaces, and data for a system to satisfy specified requirements. Systems design could be seen as the application of systems theory to product development.

Language:ShellGPL-3.0486600

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

Language:PythonNOASSERTION26587000

greedy-layer-pruning

Greedy layer pruning for transformer models.

Language:Python700

transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

Language:PythonApache-2.0163800

detr

End-to-End Object Detection with Transformers

Language:PythonApache-2.01321100

tutorials

Tutorials for creating and using ONNX models

Language:Jupyter NotebookApache-2.0330600

rockanjan