High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
Repository Index
142,273 visible repositories in the index
697–720 of 1,943 · Most stars
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
WhisperFusion builds upon the capabilities of WhisperLive and WhisperSpeech to provide a seamless conversations with an AI.
This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?
A Python package that makes it easy for developers to create AI apps powered by various AI providers.
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
- calibration
- decision-model
- jev
- jev-model
Build AI agents for your PC
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
- natural-language-processing
- chatbot
- nlp
- factuality
Measuring Massive Multitask Language Understanding | ICLR 2021
- muti-task
- transfer-learning
- gpt-3
- few-shot-learning
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
- ai-safety
- alpaca
- datasets
- deepspeed
A series of code large language models developed by PKU-KCL
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
The repository host gives no description.
Tensorflow implementation of contextualized word representations from bi-directional language models
Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.
A fork to add multimodal model training to open-r1
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
Open Academic Research on Improving LLaMA to SOTA LLM
The official repo of Pai-Megatron-Patch for LLM & VLM large scale training developed by Alibaba Cloud.
WebGLM: An Efficient Web-enhanced Question Answering System (KDD 2023)
AgentEvolver: Towards Efficient Self-Evolving Agent System
- agent
- llm
- reinforcement-learning
- self-evolving