The most streamlined road map to learn ML for free.

AI Observability & Evaluation

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

Reconquer the canvas: beautiful Tikz figures without clunky Tikz code

LLM101n: Let's build a Storyteller

Python module (C extension and plain python) implementing Aho-Corasick algorithm

Fast lexical search library implementing BM25 in Python using Scipy (on average 2x faster than Elasticsearch in single-threaded setting)

AI + Data, online. https://vespa.ai

The ultimate Vim configuration (vimrc)

Fast & Simple repository for pre-training and fine-tuning T5-style models

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Efficient few-shot learning with Sentence Transformers

Experiments for efforts to train a new and improved t5

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

Paper List for Contrastive Learning for Natural Language Processing

The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.

Octopus is a neural machine generation toolkit for Arabic Natural Lnagauge Generation (NLG)

MTEB: Massive Text Embedding Benchmark

Sparsity-aware deep learning inference runtime for CPUs

Scale LLM Engine public repository

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & C…

AraT5: Text-to-Text Transformers for Arabic Language Understanding

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

Sentiment Corpus for Swedish 🇸🇪 Norwegian 🇳🇴 Danish 🇩🇰 Finnish 🇫🇮 (and English 🏴󠁧󠁢󠁥󠁮󠁧󠁿)

Modeling, training, eval, and inference code for OLMo

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

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