DEV Community

LLM Series' Articles

Back to Jimin Lee's Series
(1/3) LLM: How LLMs Became the Bedrock of Modern AI
jiminlee profile

(1/3) LLM: How LLMs Became the Bedrock of Modern AI

#llm #machinelearning
1
Comments
4 min read
(2/3) LLM: Data, Transformers, and Relentless Compute
jiminlee profile

(2/3) LLM: Data, Transformers, and Relentless Compute

#data #ai #machinelearning #llm
1
Comments
11 min read
(3/3) LLM: In-Context Learning, Hype, and the Road Ahead
jiminlee profile

(3/3) LLM: In-Context Learning, Hype, and the Road Ahead

#llm #machinelearning
Comments
5 min read
From Word Predictor to Thinking Partner: The Rise of Thinking Models
jiminlee profile

From Word Predictor to Thinking Partner: The Rise of Thinking Models

#ai #llm #machinelearning
Comments
7 min read
Understanding Mixture of Experts (MoE)
jiminlee profile

Understanding Mixture of Experts (MoE)

#llm #machinelearning #nlp #moe
Comments
5 min read
From Full Fine-Tuning to LoRA
jiminlee profile

From Full Fine-Tuning to LoRA

#llm #machinelearning #lora #nlp
Comments
8 min read
RAG Explained
jiminlee profile

RAG Explained

#llm #machinelearning #rag
7
Comments 2
6 min read
Understanding Context Window Size in LLMs
jiminlee profile

Understanding Context Window Size in LLMs

#llm #machinelearning
1
Comments
4 min read
On-Device LLM
jiminlee profile

On-Device LLM

#llm #machinelearning #nlp #ondeviceai
3
Comments
10 min read
Why Are LLMs So Slow? And How We're Making Them Faster
jiminlee profile

Why Are LLMs So Slow? And How We're Making Them Faster

#llm #nlp #gqa
Comments
11 min read
Matryoshka Magic: How MatFormer Delivers Multi-Size Models from a Single Training
jiminlee profile

Matryoshka Magic: How MatFormer Delivers Multi-Size Models from a Single Training

#llm #nlp #matformer
Comments
8 min read
Understanding the KV Cache (feat. Self-Attention)
jiminlee profile

Understanding the KV Cache (feat. Self-Attention)

#llm #nlp #kvcache
Comments
12 min read