📖 Qiyao Wang's Blog
Total Blogs
2025
- Feb. 27, 2025. Three Sampling Methods: Temperature, Top K and Top P. Language: Chinese. #Decoding
- Feb. 26, 2025. Greedy Search and Beam Search. Language: Chinese. #Decoding
- Feb. 25, 2025. Autoregressive Decoding: Basic Manner of Decoder-Only LLMs. Language: Chinese. #Decoding
- Feb. 24, 2025. Proximal Policy Optimization (PPO) and RLHF. Language: Chinese. #RL
- Feb. 23, 2025. Basic Knowledge of Reinforcement Learning before PPO. Language: Chinese. #RL
- Jan. 08, 2025. CMU DLSys Course Homework 1: Implementation and Reflection (Part1). Language: Chinese. #MLSys
- Jan. 07, 2025. Chain-of-Thought Reasoning without Prompting. Language: Chinese. #Reasoning
- Jan. 01, 2025. CMU DLSys Course Homework 0: Implementation and Reflection. Language: Chinese. #MLSys
2024
- Dec. 28, 2024. Pattern Recognition and Machine Learning. Language: Chinese. #ML