Aohan Zeng (Sengxian)

Sengxian

Geek Repo

Company:DCST, Tsinghua University

Location:Beijing, China

Home Page:https://blog.sengxian.com/

Github PK Tool:Github PK Tool

Aohan Zeng's starred repositories

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

Language:PythonLicense:Apache-2.0Stargazers:39704Issues:395Issues:1286

alist

🗂️A file list/WebDAV program that supports multiple storages, powered by Gin and Solidjs. / 一个支持多存储的文件列表/WebDAV程序,使用 Gin 和 Solidjs。

Language:GoLicense:AGPL-3.0Stargazers:38549Issues:188Issues:3256

typst

A new markup-based typesetting system that is powerful and easy to learn.

Language:RustLicense:Apache-2.0Stargazers:29280Issues:82Issues:2157

srs

SRS is a simple, high-efficiency, real-time video server supporting RTMP, WebRTC, HLS, HTTP-FLV, SRT, MPEG-DASH, and GB28181.

ChatGLM2-6B

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

Language:PythonLicense:NOASSERTIONStargazers:15555Issues:135Issues:615

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Language:PythonLicense:NOASSERTIONStargazers:14197Issues:264Issues:201

Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Language:PythonLicense:Apache-2.0Stargazers:11812Issues:96Issues:1015

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:11464Issues:106Issues:821

GLM-130B

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Language:PythonLicense:Apache-2.0Stargazers:7630Issues:98Issues:198

CodeGeeX2

CodeGeeX2: A More Powerful Multilingual Code Generation Model

Language:PythonLicense:Apache-2.0Stargazers:7388Issues:63Issues:232

AITemplate

AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

Language:PythonLicense:Apache-2.0Stargazers:4469Issues:82Issues:240

x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers

Language:PythonLicense:MITStargazers:4252Issues:52Issues:197

wireproxy

Wireguard client that exposes itself as a socks5 proxy

Language:GoLicense:ISCStargazers:4051Issues:25Issues:73

awesome-resume-for-chinese

:page_facing_up: 适合中文的简历模板收集(LaTeX,HTML/JS and so on)由 @hoochanlon 维护

VisualGLM-6B

Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

Language:PythonLicense:Apache-2.0Stargazers:4007Issues:40Issues:345

switch-lan-play

Enjoy games with your friends as if you were on a LAN.

Language:CLicense:GPL-3.0Stargazers:1786Issues:46Issues:135

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

Language:PythonLicense:Apache-2.0Stargazers:1527Issues:34Issues:222

fastmoe

A fast MoE impl for PyTorch

Language:PythonLicense:Apache-2.0Stargazers:1430Issues:12Issues:113

AgentTuning

AgentTuning: Enabling Generalized Agent Abilities for LLMs

chatgpt-comparison-detection

Human ChatGPT Comparison Corpus (HC3), Detectors, and more! 🔥

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Language:PythonLicense:MITStargazers:1066Issues:19Issues:80

SwissArmyTransformer

SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.

Language:PythonLicense:Apache-2.0Stargazers:856Issues:30Issues:72

XrayGLM

🩺 首个会看胸部X光片的中文多模态医学大模型 | The first Chinese Medical Multimodal Model that Chest Radiographs Summarization.

Language:PythonLicense:NOASSERTIONStargazers:826Issues:8Issues:74

Chinese_segment_augment

python3实现互信息和左右熵的新词发现

ikago

IkaGo is a proxy which helps bypassing UDP blocking, UDP QoS and NAT firewall written in Go.

Language:GoLicense:MITStargazers:527Issues:9Issues:5

word-discovery

速度更快、效果更好的中文新词发现

marlin

FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.

Language:PythonLicense:Apache-2.0Stargazers:390Issues:13Issues:20

flutter_live

Live streaming player, iOS+Android, RTMP/HTTP-FLV/HLS/WebRTC, by Flutter+SRS.

Language:JavaScriptLicense:MITStargazers:314Issues:10Issues:16

vdi-stream-client

VDI Stream Client is a very tiny, low latency and GPU accelerated client to connect to Windows running Parsec Host.

Language:CLicense:GPL-3.0Stargazers:122Issues:5Issues:8

riscv-syntax

RISC-V syntax adapted from MIPS syntax highlightning package for sublime text 2

Language:PythonStargazers:8Issues:0Issues:0