🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Support deepseek-r1

🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…

A Gradio web UI for Large Language Models with support for multiple inference backends.

MLX: An array framework for Apple silicon

Distribute and run LLMs with a single file.

Use your locally running AI models to assist you in your web browsing

Let your Claude able to think

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, and more.

Make websites accessible for AI agents

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

Implementation of the convolutional module from the Conformer paper, for use in Transformers

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

O1 Replication Journey

Model API for GALACTICA

Awesome-LLM: a curated list of Large Language Model

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

This is a Phi Family of SLMs book for getting started with Phi Models. Phi a family of open sourced AI models developed by Microsoft. Phi models are the most capable and cost-effective small langua…

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

SOTA Open Source TTS

Finetune Llama 3.3, DeepSeek-R1, Mistral, Phi-4 & Gemma 2 LLMs 2-5x faster with 70% less memory

Efficiently computes derivatives of NumPy code.

automatic differentiation made easier for C++

LLM inference in C/C++

🚀🚀 「大模型」3小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 3 hours!