Python bindings for llama.cpp
Structured outputs for llms
Run Local LLMs on Any Device. Open-source
Port of Facebook's LLaMA model in C/C++
Powerful AI language model (MoE) optimized for efficiency/performance
Open-source, high-performance AI model with advanced reasoning
Low-code app builder for RAG and multi-agent AI applications
A high-throughput and memory-efficient inference and serving engine
A modular graph-based Retrieval-Augmented Generation (RAG) system
Open-source end-to-end LLM Development Platform
C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Ongoing research training transformer models at scale
Open-source observability for your LLM application
Building applications with LLMs through composability
BISHENG is an open LLM devops platform for next generation apps
Framework and no-code GUI for fine-tuning LLMs
Access large language models from the command-line
Integrate cutting-edge LLM technology quickly and easily into your app
lightweight package to simplify LLM API calls
Toolkit for conversational AI
Application that simplifies the installation of AI-related projects
The unofficial python package that returns response of Google Bard
Interact with your documents using the power of GPT
PyTorch library of curated Transformer models and their components