Farming Tong's repositories
3DTrans
An Open-source Codebase for exploring Continuous-learning/Pre-training-oriented Autonomous Driving Task
AcademiCodec
AcademiCodec: An Open Source Audio Codec Model for Academic Research
BillyGPT
可自动优化提示、免费开源、全平台傻瓜式 ChatGPT 本地客户端，支持断点续聊、修改历史对话、本地聊天记录存储导入导出、添加自己的 apikey
BMTools
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
carefree-drawboard
🎨 Infinite Drawboard in Python
ChatGPT
ChatGPT
ChatNote
Notes taking powered by ChatGPT
CouloyDB
CouloyDB is a KV store engine based on bitcask model
Deep-RL-Notes
A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)
DIFFormer
The official implementation for ICLR23 spotlight paper "DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion"
FLFormer
1st prize method for CVPR2022 Workshop "Vision for All Seasons"
Generalizable-Mixture-of-Experts
GMoE could be the next backbone model for many kinds of generalization task.
golang-internal
This project features optimized Go language, expert source code, concurrent processing, and industry-best practices.
LAformer
Official PyTorch Implementation of "LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints"
legal-prompts-for-gpt
An opensource legal prompts
light-gpt
Light-GPT is an interactive website project based on the GPT-3.5-Turbo Model.
mmap-bloom-filter
基于硬盘的布隆过滤器，使用虚拟内存支持万亿级去重特性
netdev
基于fastapi实现简单网络自动化后端服务
omnisafe
OmniSafe is a comprehensive and reliable benchmark for safe reinforcement learning.
Otter
🦦 Otter, an instruction-tuned model built upon OpenFlamingo that has been customized for a context.
PRipple
(脉冲涟漪)
RepAdapter
Official implementation of "Towards Efficient Visual Adaption via Structural Re-parameterization".
search-legend
docs for search system and ai infra
Segment-and-Track-Anything
An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.
UNINEXT
[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval
xxim-server
惺惺 —— 属于你的社交地盘！惺惺是一个100%开源社交平台，每个人都可以搭建自己的服务器，掌握数据的所有权。此APP非盈利项目！
YeeZ-Privacy-Computing
Fidelius - YeeZ Privacy Computing