Stars
â• Share quick reference cheat sheet for developers.
A unified, comprehensive and efficient recommendation library
A django website used in the book Practical Recommender Systems to illustrate how recommender algorithms can be implemented.
Access a database of word frequencies, in various natural languages.
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Distributed Asynchronous Hyperparameter Optimization in Python
An open collection of implementation tips, tricks and resources for training large language models
An open collection of methodologies to help with successful training of large language models.
quantity-aware lexical and semantic models for answering quantity-centric queries
Robust recipes to align language models with human and AI preferences
Example models using DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
A lunar calendar converter in Python, including 24 solar terms and a number of solar holidays and lunar holidays, mainly from China.
Utils for converting between date formats and calculating holidays
DSPy: The framework for programming—not prompting—language models
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Smatch tool: evaluation of AMR semantic structures
A guidance language for controlling large language models.
BLEURT is a metric for Natural Language Generation based on transfer learning.
Official style files for papers submitted to venues of the Association for Computational Linguistics
Set of tools to assess and improve LLM security.