Ma-Dan

matmulfreellm

Implementation for MatMul-free LM.

duix.ai

mi-gpt

🏠 将小爱音箱接入 ChatGPT 和豆包，改造成你的专属语音助手。

How_to_optimize_in_GPU

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

MuseTalk

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

MuseV

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

vt-transformer

Transformer framework for edge computing based on C++.

GLM-4

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大语言模型提供更高质量、更丰富、更易”消化“的数据！

ipex-llm

Accelerate local LLM inference and finetuning (LLaMA, Mistral, ChatGLM, Qwen, Baichuan, Mixtral, Gemma, Phi, etc.) on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max); seamlessly integrate with llama.cpp, Ollama, HuggingFace, LangChain, LlamaIndex, DeepSpeed, vLLM, FastChat, Axolotl, etc.

yuren-baichuan-7b

基于baichuan-7b的开源多模态大语言模型

llama3-from-scratch-zh

从零实现一个 llama3 中文版

ChatTTS

ChatTTS is a generative speech model for daily dialogue.

DeepFilterNet

Noise supression using deep filtering

OpsPilot

OpsPilot是WeOps团队开源的一个基于深度学习与LLM技术的智能运维助理，以运维大脑的形态，联动各类运维系统，提供智能化运维的能力支撑。

TeleSpeech-ASR

awesome-LLMs-In-China

**大模型

moondream

tiny vision language model

cutlass_grouped_gemm

PyTorch bindings for CUTLASS grouped GEMM.

mlc-MiniCPM

MiniCPM on Android platform.

MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone

SLAM-LLM

Speech, Language, Audio, Music Processing with Large Language Model

langgraph

Build resilient language agents as graphs.

rag-from-scratch

ai-voice-cloning

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

hiddenlayer

Neural network graphs and training metrics for PyTorch, Tensorflow, and Keras.

WeChatFerry

微信机器人底层框架，可接入Gemini、ChatGPT、ChatGLM、讯飞星火、Tigerbot等大模型。WeChat Robot Hook.

libllm

Efficient inference of large language models.