Stars
A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.
A modern cookiecutter template for Python projects that use uv for dependency management
♞ lichess.org: the forever free, adless and open source chess server ♞
A repository for analyzing the impact of co-occurrence statistics on factual knowledge of large language models (EMNLP 2023 Findings).
A high performance python hash table library that is generally faster and consumes significantly less memory than Python Dictionaries
Python disk-backed cache (Django-compatible). Faster than Redis and Memcached. Pure-Python.
A guidance language for controlling large language models.
A web-based collaborative LaTeX editor
MARISA: Matching Algorithm with Recursively Implemented StorAge
Efficient and general syntactical decoding for Large Language Models
Enforce the output format (JSON Schema, Regex etc) of a language model
🤗 A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformers
New generation entropy codecs : Finite State Entropy and Huff0
FastAC - Amir Said's Arithmetic and Huffman coding library, example code, and documentation
WikiFactDiff is a factual atomic knowledge update dataset for LLMs. It describes the evolution of factual knowledge between two dates.
Web mining module for Python, with tools for scraping, natural language processing, machine learning, network analysis and visualization.
A Python library to conjugate verbs in French, English, Spanish, Italian, Portuguese and Romanian (more soon) using Machine Learning techniques.
Large scale graph learning on a single machine.
[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.