返回笔记列表
CS336
课程笔记
17 篇笔记
0 个标签
1
CS336: Language Models from Scratch (Lecture 1)
2
CS336: PyTorch Primitives & Resource Accounting (Lecture 2)
3
LLM 架构与超参数 (Architectures and Hyperparameters)
4
Mixture of Experts (MoE) From Scratch to DeepSeek V3
5
GPU 架构与大模型高效计算 (GPU Architecture & Efficient Computing for LLMs)
6
GPU 高性能编程与内核优化 (High Performance GPU Programming & Kernels)
7
Parallelism 1 (Multi-Machine Optimization)
8
大规模语言模型训练——并行计算基础 (Parallelism 2)
9
Scaling Laws (Part 1) - 基础与数据/模型扩展
10
从零构建语言模型 (Language Modeling from Scratch) - 第10讲：推理 (Inference)
11
Scaling Laws 2 (扩展定律进阶与实战)
12
斯坦福 CS336：从零构建语言模型 (Language Modeling from Scratch)
13
CS336 Language Modeling from Scratch | Lecture 13: Data 1
14
CS336 Language Modeling from Scratch
15
Stanford CS336 Lecture 15: Alignment - Supervised Fine-Tuning (SFT) & RLHF
16
Alignment - RL from Verifiable Rewards (基于可验证奖励的强化学习)
17