RunByAI

Tag: large model

73 post(s)

October 6, 20260 comment(s)

Introduction to Activation Function: Why Neural Networks Cannot Do Without Nonlinear Switches

If there is only matrix multiplication, even the deepest neural network will only be a large linear transformation, and it will not have complex patterns at all. What truly brings neural networks to l

Tech Guide deep learning large model

October 6, 20260 comment(s)

Introduction to Decoding Strategies: How Big Models "Choose the Next Word"

When a big model completes a sentence, it faces tens of thousands or even tens of thousands of candidate words. Why does it pick out the next one? Why is the same question sometimes answered steadily

Tech Guide large model Reasoning optimization

October 6, 20260 comment(s)

Introduction to Speculative Decoding: How LLMs Speed Up Inference by Guessing and Verifying

Most people who have used local large models have a common experience: typing is too slow. Especially in dialogue based generation, the model must squeeze out each token one by one, making it difficul

Tech Guide large model Reasoning optimization

October 5, 20260 comment(s)

Introduction to Chain of Thought: Why Big Models Think Step by Step More Accurately

Why can the same big model sometimes provide quick and incorrect answers, but sometimes it can reliably deduce results? The difference often lies not in the model itself, but in 'how to ask'. The Chai

Tech Guide large model

October 3, 20260 comment(s)

Introduction to Knowledge Graph: How AI "connects knowledge into a web"

What is a knowledge graphKnowledge Graph uses a triplet of "entity relationship entity" to organize scattered knowledge into a searchable and inferential network. For example, (Beijing, the capital, C

Tech Guide large model

September 30, 20260 comment(s)

Introduction to Scaling Laws: Why "bigger" often means "stronger"

In the past few years, the most counterintuitive and important discovery in the field of AI can be summarized in one sentence: making models bigger, data more, and computing power more abundant often

Tech View large model Large Language Model (LLM)

September 26, 20260 comment(s)

Introduction to Loss Functions: How Large Models Score Themselves with Cross-Entropy

Training a large model is essentially letting it keep guessing the next word and then adjusting itself based on whether the guess was right. The ruler that measures how good the guess is, is the loss

Tech Guide large model Large Language Model (LLM)

September 26, 20260 comment(s)

Introduction to Gradient Accumulation: How to Simulate a Large Batch with Limited GPU Memory

When training large models we often hit a conflict: we want a larger batch size for more stable gradient estimates, but GPU memory will not fit it. Gradient accumulation is the classic trick that reso

Tech Guide large model Large Language Model (LLM)

September 26, 20260 comment(s)

Introduction to LLM Routing: How to Route Requests of Different Difficulty to the Right Model

Many applications handle requests of wildly different difficulty: some are simple format conversions, others need multi-step reasoning. Sending everything to the strongest model may give the best answ

Tech Guide large model Large Language Model (LLM)

September 26, 20260 comment(s)

Introduction to Prompt Caching: How to Save Cost and Latency by Repeatedly Calling Large Model APIs

Many large model applications share a common feature: each request must be accompanied by the same long and fixed content - system prompt words, product descriptions, knowledge base fragments, code sp

Tech Guide large model Large Language Model (LLM)

73 post(s)

...