High-level, high-performance dynamic language for technical computing
The Classical Language Toolkit
Python bindings for llama.cpp
NLP Cloud serves high performance pre-trained or custom models for NER
Structured outputs for llms
Robust Speech Recognition via Large-Scale Weak Supervision
Run Local LLMs on Any Device. Open-source
Vector Database for the next generation of AI applications
Port of Facebook's LLaMA model in C/C++
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
A modular, primitive-first, python-first PyTorch library
A gradio web UI for running Large Language Models like LLaMA
INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Powerful AI language model (MoE) optimized for efficiency/performance
Open-source, high-performance AI model with advanced reasoning
A guidance language for controlling large language models
Telegram Drive
LMDeploy is a toolkit for compressing, deploying, and serving LLMs
Full stack AI software engineer
A high-throughput and memory-efficient inference and serving engine
Speech-to-text, text-to-speech, and speaker recognition
A refreshing functional take on deep learning
Deep universal probabilistic programming with Python and PyTorch
Sparsity-aware deep learning inference runtime for CPUs
Phi-3.5 for Mac: Locally-run Vision and Language Models