ghbacct

BERTopic

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Top2Vec

Top2Vec learns jointly embedded topic, document and word vectors.

texthero

Text preprocessing, representation and visualization from zero to hero.

token-list

prodigy-tui

A textual TUI for Prodigy

machine-learning-for-software-engineers

A complete daily plan for studying to become a machine learning engineer.

100-Days-Of-ML-Code

100 Days of ML Coding

data-science-interviews

Data science interview questions and answers

gpt-investor

dockerLLM

TheBloke's Dockerfiles

aici

AICI: Prompts as (Wasm) Programs

Daft

Distributed DataFrame for Python designed for the cloud, powered by Rust

drawdata

Draw datasets from within Jupyter.

feature-engineering-az

Source for book "Feature Engineering A-Z"

hamilton

Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage and metadata. Runs and scales everywhere python does.

llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

mergekit

Tools for merging pretrained large language models.

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

Flowise

Drag & drop UI to build your customized LLM flow

self-rag

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

instructor

structured outputs for llms

shaderunner

Ctrl + F but fancy.

newsy

ML-Papers-Explained

Explanation to key concepts in ML

projects

🪐 End-to-end NLP workflows from prototype to production

nlpaug

Data augmentation for NLP

ml-engineering

Machine Learning Engineering Open Book

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

useb

Heterogenous, Task- and Domain-Specific Benchmark for Unsupervised Sentence Embeddings used in the TSDAE paper: https://arxiv.org/abs/2104.06979.