bugm's starred repositories
annotated_deep_learning_paper_implementations
🧑🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
Chinese-LLaMA-Alpaca
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
gpt4-pdf-chatbot-langchain
GPT4 & LangChain Chatbot for large PDF docs
llama3-from-scratch
llama3 implementation one matrix multiplication at a time
PaLM-rlhf-pytorch
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
pdfplumber
Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.
missing-semester-cn.github.io
the CS missing semester Chinese version
pdfminer.six
Community maintained fork of pdfminer - we fathom PDF
OpenPrompt
An Open-Source Framework for Prompt-Learning.
latent-consistency-model
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Alpaca-CoT
We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台,我们欢迎开源爱好者发起任何有意义的pr!
Awesome-LLM-Inference
📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.
ChatGenTitle
🌟 ChatGenTitle:使用百万arXiv论文信息在LLaMA模型上进行微调的论文题目生成模型
unlikelihood_training
Neural Text Generation with Unlikelihood Training
awesome-azure-openai-llm
"Awesome-LLM: a curated list of Azure OpenAI & Large Language Models" 🔎References to Azure OpenAI, 🦙Large Language Models, and related 🌌 services and 🎋libraries.
benchmarks
Benchmarking PDF libraries
The-Power-of-Noise
Code and data for "The Power of Noise: Redefining Retrieval for RAG Systems"