Lists (1)
Stars
Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.
Distribute and run LLMs with a single file.
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Superlinked is a Python framework for AI Engineers building high-performance search & recommendation applications that combine structured and unstructured data.
AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.
A modern Python package and dependency manager supporting the latest PEP standards
Easy token price estimates for 400+ LLMs. TokenOps.
Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪
Video+code lecture on building nanoGPT from scratch
AI Tool for querying natural language on tabular data.
rahulunair / pipecat
Forked from pipecat-ai/pipecatOpen Source framework for voice and multimodal conversational AI
Accelerate LLM with low-bit (FP4 / INT4 / FP8 / INT8) optimizations using ipex-llm
SYCL implementation of Fused MLPs for Intel GPUs
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer
nanobind: tiny and efficient C++/Python bindings
Farmers helper bot using Intel One API and Gemma-2B and Gemini Pro
lightweight, standalone C++ inference engine for Google's Gemma models.
Mamba-Chat: A chat LLM based on the state-space model architecture 🐍
TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.