Lists (1)
Stars
A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).
A high-throughput and memory-efficient inference and serving engine for LLMs
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句，基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
CS33作业 2 的代码和飞书 qa, 这个作业太恶心了, 绝对是所有作业里面花的最久的
Puzzles for learning Triton, play it with minimal environment configuration!
A gently curated list of companies using verification formal methods in industry
My Solution and Notes for the Stanford CS336: LLM from scratch
DistAI: Data-Driven Automated Invariant Learning for Distributed Protocols
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
[COLM 2024] A Survey on Deep Learning for Theorem Proving
Implementation from Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
PyTorch implementation of "Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference"