📚 Process PDFs, Word documents and more with spaCy

Code and data of AAAI 2023 paper "Improving Biomedical Entity Linking with Cross-Entity Interaction".

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

Creating beautiful plots of data maps

Instrument your FastAPI with Prometheus metrics.

A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.

A python module for evaluating NERC and NEL system performances as defined in the HIPE shared tasks (formerly CLEF-HIPE-2020-scorer).

Create a Geonames gazetteer index in Elasticsearch

An API to geocode and reverse-geocode against the Geonames gazetteer

geocoding and geolocalisation webservices for Geonames, Openstreetmap, Openaddresses, Tiger and quattroshapes data

Foundation Model Evaluations Library

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A 4-hour coding workshop to understand how LLMs are implemented and used

Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]

Rapidly build AI apps in Python

Hunt down social media accounts by username across social networks

Python scraper based on AI

An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)

GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embeddings

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Repository for the paper "Automated Hate Speech Detection and the Problem of Offensive Language", ICWSM 2017

Codes for SHINE published in EMNLP 2021.

AI models for automatic job application pipeline (user CV, job description analysis (customized NER/SpaCy) and artificial cover letter generation (trained GPT-2 model) created for Jobzilla project …

The Spanish Fake News Corpus contains a collection of 971 news divided into 491 real news and 480 fake news. The corpus covers news from 9 different topics: Science, Sport, Economy, Education, Ente…

Automatically create Faiss knn indices with the most optimal similarity search parameters.

Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory

Run Mixtral-8x7B models in Colab or consumer desktops

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