strategist922
PhD Student, Department of Computer Science and Technology Tsinghua University, China
MicrosoftTaipei, Taiwan
Pinned Repositories
aioshadowsocks
用 asyncio 重写 shadowsocks ~
Air-Universe
开源多功能机场后端, 协议支持 V2Ray(VMess), Trojan, Shadowsocks(单端口多用户);面板支持 SSPanel, v2board, django-sspanel.
arweave-python-client
This client allows you to integrate your python apps with the Arweave network allowing you to perform wallet operations and transactions
ArweaveApps
Permaweb indexer for permaweb apps built on top of Arweave.
Awesome-LLM-for-RecSys
Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
modbus-tk
Create Modbus app easily with Python
NtMiner
GPU miner.因为github网速较慢,改在https://gitee.com/ntminer/NTMiner 更新,累积变化后才会更新到这里。
NvidiaRTX-LHRv2Unlocker
The first fully automated BIOS modifier for RTX cards with LHR v2 lock.
sspanel-malio
strategist922's Repositories
strategist922/xLAM
strategist922/Agent-FLAN
Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models
strategist922/ATLAS
A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171
strategist922/automatic-KG-creation-with-LLM
Automatic Ontology and Knowledge Graph construction with LLM
strategist922/ChatGPT-Next-Web
A cross-platform ChatGPT/Gemini UI (Web / PWA / Linux / Win / MacOS). 一键拥有你自己的跨平台 ChatGPT/Gemini 应用。
strategist922/depth-fm
DepthFM: Fast Monocular Depth Estimation with Flow Matching
strategist922/EDTalk
The official repository of the paper EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis
strategist922/FRESCO
[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
strategist922/GenN2N
[CVPR'24 - Rebuttal Score 554] GenN2N: Generative NeRF2NeRF Translation
strategist922/gpt-llm-trainer
strategist922/gpt-prompt-engineer
strategist922/img2img-turbo
One-step image-to-image with Stable Diffusion turbo: sketch2image, day2night, and more
strategist922/LAV-DF
[CVIU] Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization
strategist922/llamafile
Distribute and run LLMs with a single file.
strategist922/LLMLingua
To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
strategist922/LMFlow
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
strategist922/Long-CLIP
strategist922/MDT
Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)
strategist922/mPLUG-DocOwl
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
strategist922/PointMamba
PointMamba: A Simple State Space Model for Point Cloud Analysis
strategist922/RelayDiffusion
The official implementation of "Relay Diffusion: Unifying diffusion process across resolutions for image synthesis" [ICLR 2024 Spotlight]
strategist922/RSMamba
This is the pytorch implement of the paper "RSMamba: Remote Sensing Image Classification with State Space Model"
strategist922/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.
strategist922/RWKV-Runner
A RWKV management and startup tool, full automation, only 8MB. And provides an interface compatible with the OpenAI API. RWKV is a large language model that is fully open source and available for commercial use.
strategist922/stable-diffusion
A latent text-to-image diffusion model
strategist922/V2L-Tokenizer
strategist922/video-mamba-suite
The suite of modeling video with Mamba
strategist922/VMamba
VMamba: Visual State Space Models,code is based on mamba
strategist922/XAgent
An Autonomous LLM Agent for Complex Task Solving
strategist922/xformers
Hackable and optimized Transformers building blocks, supporting a composable construction.