Pinned Repositories
agency-swarm
An opensource agent orchestration framework built on top of the latest OpenAI Assistants API.
agency-swarm-lab
AppBlockMainFrame
A simple project to prevent using application when you are studying or working
Cheat-Sheet
Here are some common algorithm problem-solving templates
code_review_log
codeforces
一个每日刷codeforces的记录
princepride
scratch-pytorch-step-by-step
教你只用最基本的python语法和numpy一步步实现深度学习框架
Speakup_v2
Speakup_v2
video-trans
video-trans
princepride's Repositories
princepride/scratch-pytorch-step-by-step
教你只用最基本的python语法和numpy一步步实现深度学习框架
princepride/princepride
princepride/Cheat-Sheet
Here are some common algorithm problem-solving templates
princepride/code_review_log
princepride/Speakup_v2
Speakup_v2
princepride/video-trans
video-trans
princepride/agency-swarm
An opensource agent orchestration framework built on top of the latest OpenAI Assistants API.
princepride/agency-swarm-lab
princepride/diary
A diary to record my life
princepride/fine-tune
一个关于微调的教程,还有各种demo
princepride/LAVIS
LAVIS - A One-stop Library for Language-Vision Intelligence
princepride/Llava
Llava
princepride/personal-website
My personal website source code
princepride/super_llama3
princepride/useful-tools
useful-tools
princepride/bitsandbytes
Accessible large language models via k-bit quantization for PyTorch.
princepride/champ
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
princepride/ChatTTS
ChatTTS is a generative speech model for daily dialogue.
princepride/ColossalAI
Making large AI models cheaper, faster and more accessible
princepride/InternVL
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
princepride/JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
princepride/long_story_video_creator
Generate corresponding long videos based on your script and lines, using RPA and Genmo
princepride/MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型,实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO。
princepride/Open-Sora
Open-Sora: Democratizing Efficient Video Production for All
princepride/OpenRLHF
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)
princepride/ProactiveAgent
A LLM-based Agent that predict its tasks proactively.
princepride/pytorch-book
PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch:入门与实战》)
princepride/ragas
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
princepride/ShiArthur03
princepride/tarsier
Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.