Tag
35articles · across 2 categories
#Concept
- 20264 entries
- MAGRPO: Training LLMs That Truly Collaborate with Multi-Agent Reinforcement Learning阅读Jun 25
- From MDP to Dec-POMDP: Understanding the Differences Between Single-Agent and Multi-Agent Decision Models阅读Jun 25
- LLM 基础概念分享：从原理到 Function Call -> MCP -> Agent -> Skills技术Feb 10
- 从 Prompt Engineering 演进到 Agent（Role → Step-by-step → Few-shot → Thinking → ReAct）技术Feb 10
- 202523 entries
- Model Context Protocol (MCP) Architecture技术Mar 6
- Model Context Protocol (MCP) Introduction技术Mar 6
- 图解Transoformer学习 (Attention Mechanism)技术Feb 24
- Fine-tuning to follow instructions 3. Evaluating the fine-tuned LLM技术Feb 21
- Fine-tuning to follow instructions 2. Setup Model and Fine-tuning技术Feb 21
- Fine-tuning to follow instructions 1. Prepare dataset and Create data loader技术Feb 20
- Fine-tuning for classification 3. Fine-tuning Model技术Feb 19
- Fine-tuning for classification 2. Setup Model And Prepare Loss Calcutation技术Feb 19
- Deepseek的Native Sparse Attention方向技术Feb 19
- Fine-tuning for classification 1. Prepare dataset and Create data loader技术Feb 18
- Pretraining GPT model with unlabeled data 4. Load and save model weights技术Feb 13
- Pretraining GPT model with unlabeled data 3. Decoding strategies to control randomness技术Feb 13
- Pretraining GPT model with unlabeled data 2. Training an LLM技术Feb 12
- Pretraining GPT model with unlabeled data 1.Evaluating generative text models技术Feb 12
- 神经网络的基石：梯度、损失、学习率、权重与偏置的深度剖析技术Feb 12
- Implement a GPT model 5. GPT model & Generating text技术Feb 12
- Implement a GPT model 4. Shortcut Connections & Transformer Block技术Feb 11
- Implement a GPT model 3. FeedForward network with GELU activations技术Feb 11
- 推理模型分类与对比技术Feb 11
- Implement a GPT model 2.Normalizing activations with layer normalization技术Feb 11
- Reinforcement Learning(RL) & Reinforcement Learning from Human Feedback (RLHF)技术Feb 10
- Implement a GPT model 1. LLM architecture技术Feb 10
- 分布式单体：你可能从未真正构建过微服务技术Feb 10
- 20248 entries
- Self-Attention 4. Single-head Attention to Multi-head Attention技术Nov 13
- Self-Attention 3. Causal attention技术Nov 11
- Self-Attention 2. trainable weights技术Oct 28
- Self-Attention 1. attention weight技术Oct 25
- Next.js 与 React 关系技术Oct 12
- BPE(byte-pair-encoding)技术Oct 8
- 高级RAG技术Jun 11
- 网络IO技术Apr 29
Appears in