alexandres

hoppscotch

Open source API development ecosystem - https://hoppscotch.io (open-source alternative to Postman, Insomnia)

nanoGPT

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

minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

stanford-cs-229-machine-learning

VIP cheatsheets for Stanford's CS 229 Machine Learning

mamba

Mamba SSM architecture

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

hugo-PaperMod

A fast, clean, responsive Hugo theme.

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

marimo

A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.

alive-progress

A new kind of Progress Bar, with real-time throughput, ETA, and very cool animations!

promptfoo

Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.

ml-mgie

mistral.rs

Blazingly fast LLM inference.

vcrpy

Automatically mock your HTTP interactions to simplify and speed up testing

direct-preference-optimization

Reference implementation for DPO (Direct Preference Optimization)

Awesome-LLM-Reasoning

Reasoning in Large Language Models: Papers and Resources, including Chain-of-Thought and OpenAI o1 🍓

DataScienceInteractivePython

Python interactive dashboards for learning data science

betamax

A VCR imitation designed only for python-requests.

crowd-kit

Control the quality of your labeled data with the Python tools you already know.

pymer4

All the convenience of lme4 in python

fastfit

FastFit ⚡ When LLMs are Unfit Use FastFit ⚡ Fast and Effective Text Classification with Many Classes

echo-embeddings

infix

A Clojure library for expressing LISP expressions as infix rather than prefix notation

ml-annotate

Use ML-Annotate to label data for machine learning purposes

nanoGPT_mlx

Port of Andrej Karpathy's nanoGPT to Apple MLX framework.

eureka-ml-insights

A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.

Callcenter-Simulator

Callcenter Simulator is a free, platform-independent program for the analysis of staffing requirements in a call center. The simulator uses event-oriented, stochastic simulation for the computation of the parameters.

paired-perm-test

Exact paired permutation significance test for accuracy

Ranked-List-Truncation

A framework for Ranked List Truncation, including the implementation of multiple existing deep models, such as BiCut、Choopy and AttnCut. And we propose the multi-task model based on these models.

DQN

Dynamic routing policies for multi-skill call centers using Deep Q Network