1310, 2026 KL散度与交叉熵的区别 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More
1310, 2026 KL Divergence vs. Cross-Entropy 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 0 comments Read More
1310, 2026 BPE分词：相邻符号如何合并 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More
1310, 2026 BPE Tokenization: How Symbols Merge 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 0 comments Read More
1310, 2026 Softmax：为什么要减最大值 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More
1310, 2026 Softmax: Why Subtract the Maximum 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More
1310, 2026 AMD Helion：Agent为何需要CPU机架 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 0 comments Read More
1310, 2026 AMD Helion: Why Agents Need CPU Racks 黎 浩然/ 13 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 0 comments Read More
1210, 2026 困惑度PPL怎么算 黎 浩然/ 12 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More
1210, 2026 How to Calculate Perplexity 黎 浩然/ 12 10 月, 2026/ 大语言模型/LARGELANGUAGEMODEL/LLM, 机器学习/MACHINELEARNING, 研究生/POSTGRADUATE, 计算机/COMPUTER/ 1 comments Read More