rapidai Goto Github PK

.github

3d-speaker

A repository for single- and multi-modal speaker verification, speaker recognition, and speaker diarization.

3m-asr

adlik

Adlik: Toolkit for Accelerating Deep Learning Inference

alpaca-cot

We extend CoT data to Alpaca to boost its reasoning ability. We are constantly expanding our collection of instruction-tuning data, and integrating more LLMs together for easy use. （我们将CoT数据扩展到Alpaca以提高其推理能力，同时我们将不断收集更多的instruction-tuning数据集,并在我们框架下集成进更多的LLM，打造一个通用的LLM-IFT平台。）

asv-subtools

An Open Source Tools for Speaker Recognition

awesome-instruction-dataset

A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

awesome-pretrained-chinese-nlp-models

Awesome Pretrained Chinese NLP Models，高质量中文预训练模型&大模型&多模态模型&大语言模型集合

awesome_llms_interview_notes

LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

bertpunc

SOTA punctation restoration (for e.g. automatic speech recognition) deep learning model based on BERT pre-trained model

bytetrack-opencv-onnxruntime

分别使用OpenCV、ONNXRuntime部署ByteTrack目标跟踪，包含C++和Python两个版本的程序

chat-ui

Open source codebase powering the HuggingChat app

chat.petals.dev

💬 Chatbot web app + HTTP and Websocket endpoints for LLM inference with the Petals client

chatglm-mnn

Pure C++, Easy Deploy ChatGLM-6B.

chatglm-tuning

一种平价的chatgpt实现方案, 基于ChatGLM-6B + LoRA

chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

chatgpt

Reverse engineered ChatGPT API

chinese-llama-2-7b

开源社区第一个能下载、能运行的中文 LLaMA2 模型！

chroma

the AI-native open-source embedding database

corundum

Open source FPGA-based NIC and platform for in-network compute

dbnet-barcode

使用DBNet检测条形码，包含C++和Python两种版本的程序

ddddocr-mnn

ddddocr mnn

donut

Official Implementation of OCR-free Document Understanding Transformer (Donut) and Synthetic Document Generator (SynthDoG), ECCV 2022

edgegpt

Reverse engineered API of Microsoft's Bing Chat AI

exllama

A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.

falcon-chat-test

A tester for falcon-40B/7B

falcontune

Tune any FALCON in 4-bit

fastasr

基于PaddleSpeech所使用的conformer模型，使用C++的高效实现模型推理，在树莓派4B等ARM平台运行也可流畅运行。

fastchat

The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"

fastestdet

:zap: A newly designed ultra lightweight anchor free target detection algorithm， weight only 250K parameters， reduces the time consumption by 10% compared with yolo-fastest, and the post-processing is simpler