yh646492956

gpt_academic

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

llama

Inference code for Llama models

faiss

A library for efficient similarity search and clustering of dense vectors.

mmdetection

OpenMMLab Detection Toolbox and Benchmark

Mask_RCNN

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

gpt4-pdf-chatbot-langchain

GPT4 & LangChain Chatbot for large PDF docs

emqx

The most scalable open-source MQTT broker for IoT, IIoT, and connected vehicles

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

faster-whisper

Faster Whisper transcription with CTranslate2

mosquitto

Eclipse Mosquitto - An open source MQTT broker

Fay

Fay is an open-source digital human framework integrating language models and digital characters. It offers retail, assistant, and agent versions for diverse applications like virtual shopping guides, broadcasters, assistants, waiters, teachers, and voice or text-based mobile assistants.

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

wenda

闻达：一个LLM调用平台。目标为针对特定环境的高效内容生成，同时考虑个人和中小企业的计算资源局限性，以及知识安全和私密性问题

text2vec

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

oneDNN

oneAPI Deep Neural Network Library (oneDNN)

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

Baichuan-13B

A 13B large language model developed by Baichuan Intelligent Technology

paho.mqtt.python

paho.mqtt.python

SadTalker-Video-Lip-Sync

本项目基于SadTalkers实现视频唇形合成的Wav2lip。通过以视频文件方式进行语音驱动生成唇形，设置面部区域可配置的增强方式进行合成唇形（人脸）区域画面增强，提高生成唇形的清晰度。使用DAIN 插帧的DL算法对生成视频进行补帧，补充帧间合成唇形的动作过渡，使合成的唇形更为流畅、真实以及自然。

mlir

"Multi-Level Intermediate Representation" Compiler Infrastructure

LLMs_interview_notes

该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

DCT-Net

Official implementation of "DCT-Net: Domain-Calibrated Translation for Portrait Stylization", SIGGRAPH 2022 (TOG); Multi-style cartoonization

EduChat

An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型，GPU部署，数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM

acoular

Acoular - Acoustic testing and source mapping software

fast-whisper-finetuning

MB-iSTFT-VITS

Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transform

kws-training-suite

cortex-m-kws

Cortex M KWS example with Tengine Lite.