Stars
Universal Romanizer that can convert any unicode script to roman (latin) script
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
A customizable Retrieval-Augmented Generation (RAG) implementation using Ollama for a private local instance Large Language Model (LLM) agent with a convenient web interface
A Python library for retrieving various linguistic information about Russian words. It provides a simple API to get synonyms, antonyms, word associations, cognate words, and definitions.
Everything you need to build state-of-the-art foundation models, end-to-end.
S-LoRA: Serving Thousands of Concurrent LoRA Adapters
Trace LLM calls (and others) and visualize them in WandB, as interactive SVG or using a streaming local webapp
Locating and editing factual associations in GPT (NeurIPS 2022)
Interpretability for sequence generation models 🐛 🔍
A tool to analyze and debug neural networks in pytorch. Use a GUI to traverse the computation graph and view the data from many different angles at the click of a button.
Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…
Open-source observability for your LLM application, based on OpenTelemetry
Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.
Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement compute-heavy dense f…
The official Python library for the OpenAI API
Instructions for running OpenVoiceOS (ex-Mycroft) with Russian locale and plans for further improvement.
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Foundational model for human-like, expressive TTS
An easy to understand TTS / SVS / SVC framework
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
Style and Grammar Checker for 25+ Languages
A high-throughput and memory-efficient inference and serving engine for LLMs
[NeurIPS 2024] Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image