LuckySJTU's Stars
bshall/hifigan
An 16kHz implementation of HiFi-GAN for soft-vc.
wookayin/gpustat
📊 A simple command-line utility for querying and monitoring GPU status
Spico197/MoE-SFT
🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts
DanKE123abc/HiPcMijia
把电脑接入小爱语音控制
Eun/MoveToDesktop
Move windows using hotkeys or the system menu
JadyXuan/NTTS
NO TIME TO SLEEP
Exgc/AVMuST-TED
SHWotever/SimHub
Multi sim dashboard, bass shaker driver, ....
wangzhenjjcn/AdobeGenp
AdobeGenp Adobe Adobe CC 2019/2020(2021/2022/2023/2024TEST) GenP Universal Patch 3.0 December 25, 2022 - Software
NVIDIA/Megatron-LM
Ongoing research training transformer models at scale
PussyCat0700/Oneflowtest
wilicc/gpu-burn
Multi-GPU CUDA stress test
eeertekin/bbcp
Securely and quickly copy data from source to target.
Xuekai-Zhu/key-configuration-of-llms
nek0us/nonebot-plugin-gpt
Nonebot2's plugin of ChatGPT
Diamondfan/cassnat_asr
Implementation of CTC alignment-based single step non-autoregressive transformer
pjlab-songcomposer/songcomposer
sobamchan/unsupervised-machine-translation-using-monolingual-corpora-only-pytorch
[WIP]
leslievan/semi-utils
一个批量添加相机机型和拍摄参数的工具,后续「可能」添加其他功能。
OpenMOSS/MOSS
An open-source tool-augmented conversational language model from Fudan University
HqWu-HITCS/Awesome-Chinese-LLM
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。
Tongji-KGLLM/RAG-Survey
Shiriluz/Word-As-Image
hkust-nlp/deita
Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]
lgc-NB2Dev/nonebot-plugin-cnrail
12306 列车时刻表查询插件
pjlab-sys4nlp/llama-moe
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training
BarRaider/streamdeck-tools
The Stream Deck Tools library wraps all the communication with the Stream Deck app, allowing you to focus on actually writing the Plugin's logic
jarobyte91/pytorch_beam_search
A lightweight implementation of Beam Search for sequence models in PyTorch.
nonebot/adapter-qq
NoneBot2 QQ 适配器 / QQ adapter for nonebot2
OpenGVLab/VideoMAEv2
[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking