AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

Replace OpenAI GPT with another LLM in your app by changing a single line of code. Xinference gives you the freedom to use any LLM you need. With Xinference, you're empowered to run inference with …

Agentic components of the Llama Stack APIs

The memory layer for Personalized AI

Ollama-friendly OpenAI Embeddings Proxy. This script bridges the gap between OpenAI's embedding API and Ollama, making it compatible with the current version of Graphrag.

Ollama Python library

A modular graph-based Retrieval-Augmented Generation (RAG) system

Fast and memory-efficient exact attention

[ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths of multiple open-source LLMs. LLM-Blender cut …

The official implementation of Self-Play Preference Optimization (SPPO)

Arena-Hard-Auto: An automatic LLM benchmark.

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

This is the Personality Core for GLaDOS, the first steps towards a real-life implementation of the AI from the Portal series by Valve.

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Robust recipes to align language models with human and AI preferences

GoMate：RAG Framework within Reliable input,Trusted output

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

The official implementation of "Aligning Large Language Models by On-Policy Self-Judgment"

A WebUI for Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

SimPO: Simple Preference Optimization with a Reference-Free Reward

Open Multilingual Chatbot for Everyone

Qwen2 is the large language model series developed by Qwen team, Alibaba Cloud.

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supportin…

MNBVC(Massive Never-ending BT Vast Chinese corpus)超大规模中文语料集。对标chatGPT训练的40T数据。MNBVC数据集不但包括主流文化，也包括各个小众文化甚至火星文的数据。MNBVC数据集包括新闻、作文、小说、书籍、杂志、论文、台词、帖子、wiki、古诗、歌词、商品介绍、笑话、糗事、聊天记录等一切形式的纯文本中文数据。

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

Retrieval Augmented Generation (RAG) chatbot powered by Weaviate

fabric is an open-source framework for augmenting humans using AI. It provides a modular framework for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

🤯 Lobe Chat - an open-source, modern-design LLMs/AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Bedrock / Azure / Mistral / Perplexity ), Multi-Modals (Vision…