-
Hunan University
Highlights
- Pro
Lists (3)
Sort Name ascending (A-Z)
Stars
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.
A high-throughput and memory-efficient inference and serving engine for LLMs
AI agents running research on single-GPU nanochat training automatically
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
The simplest, fastest repository for training/finetuning medium-sized GPTs.
🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT!🌏 Train a 64M-parameter GPT from scratch in just 2h!
微舆:人人可用的多Agent舆情分析助手,打破信息茧房,还原舆情原貌,预测未来走向,辅助决策!从0实现,不依赖任何框架。
Official inference framework for 1-bit LLMs
Free ChatGPT&DeepSeek API Key,免费ChatGPT&DeepSeek API。免费接入DeepSeek API和GPT4 API,支持 gpt | deepseek | claude | gemini | grok 等排名靠前的常用大模型。
A toolkit for developing and comparing reinforcement learning algorithms.
Automate the process of making money online.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
A generative world for general-purpose robotics & embodied AI learning.
Generative Models by Stability AI
verl: Volcano Engine Reinforcement Learning for LLMs
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Wan: Open and Advanced Large-Scale Video Generative Models
"RAG-Anything: All-in-One RAG Framework"
Minimal reproduction of DeepSeek R1-Zero
Fully local web research and report writing assistant
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7 and MiroThinker-H1, achieve 74.0 and 88.2 on the BrowseComp, respectively.
🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM!🌏 Train a 67M-parameter VLM from scratch in just 1 hours!
Google AI 2018 BERT pytorch implementation
Statistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]
Solve Visual Understanding with Reinforced VLMs