zhuleiustc1983's repositories
AcademiCodec
AcademiCodec: An Open Source Audio Codec Model for Academic Research
Anima
第一个开源的基于QLoRA的33B中文大语言模型First QLoRA based open source 33B Chinese LLM
audiolm-pytorch
Implementation of AudioLM, a SOTA Language Modeling Approach to Audio Generation out of Google Research, in Pytorch
Awesome-Document-Image-Rectification
A comprehensive list of awesome document image rectification papers.
backend
Common source, scripts and utilities for creating Triton backends.
BELLE
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
common
Common source, scripts and utilities shared across all Triton repositories.
core
The core library and APIs implementing the Triton Inference Server.
ctcdecode
PyTorch CTC Decoder bindings
ElasticSearch-Langchain-Chatglm2
Q&A based on elasticsearch+langchain+chatglm2 ｜ 基于elasticsearch，langchain，chatglm2的自有知识库问答
ewokos
A microkernel os for ARM, well ported on Raspberry Pi(s)
FastChat
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and FastChat-T5.
FasterTransformer
Transformer related optimization, including BERT, GPT
fastmoe
A fast MoE impl for PyTorch
Firefly
Firefly(流萤): 中文对话式大语言模型(全量微调+QLoRA)
langchain-ChatGLM
langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ 基于本地知识库的 ChatGLM 问答
lightweight-neural-architecture-search
This is a collection of our zero-cost NAS and efficient vision applications.
Linly
Chinese-LLaMA 、Chinese-Falcon 基础模型；ChatFlow中文对话模型；中文OpenLLaMA模型；NLP预训练/指令微调数据集
LLaMA-8bit-LoRA
Repository for Chat LLaMA - training a LoRA for the LLaMA model on HuggingFace with 8-bit quantization. Research only.
llm-foundry
LLM training code for MosaicML foundation models
MNN
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba
pandora
潘多拉，一个让你呼吸顺畅的ChatGPT。Pandora, a ChatGPT that helps you breathe smoothly.
Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
TigerBot
TigerBot: A multi-language multi-task LLM
UDIS2
ICCV2023 - Parallax-Tolerant Unsupervised Deep Image Stitching (UDIS++)
UniAudio
The Open Source Code of UniAudio
vall-e
PyTorch implementation of VALL-E(Zero-Shot Text-To-Speech), Reproduced Demo https://lifeiteng.github.io/valle/index.html