Easy-to-use and high-performance NLP and LLM framework
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models
A tool for learning vector representations of words and entities
Trained models & code to predict toxic comments
Data and tools for generating and inspecting OLMo pre-training data
Fast and customizable framework for automatic ML model creation
A coding-free framework built on PyTorch
Efficient Retrieval Augmentation and Generation Framework
A Heterogeneous Benchmark for Information Retrieval
A full spaCy pipeline and models for scientific/biomedical documents
Libraries for applying sparsification recipes to neural networks
The no-nonsense RAG chunking library
An easy-to-use LLMs quantization package with user-friendly apis
An LLM-powered knowledge curation system that researches topics
LLM based data scientist, AI native data application
FastAPI server-side rendering with built-in HTMX support.
Open Source Cybersecurity Threat Hunting Platform
A generic, spec-compliant, thorough implementation of the OAuth
Tools like web browser, computer access and code runner for LLMs
pg_activity is a top like application for PostgreSQL server activity
ReFT: Representation Finetuning for Language Models
A guidance language for controlling large language models
ROS packages for Turtlebot3
The OWASP MASVS (Mobile Application Security Verification Standard)
Automate code reviews, patching and documentation