Verified65% confidenceFactExact time
Large language models are divided into two major types: base models (Base LLM) and instruction-tuned models (Instruction-tuned LLM)
3
Sources
65%
Confidence
Long-term
Relevance
7/6/2026
First Seen
Sources
Andrew Ng's Prompt Engineering Course: How Developers Call LLMs via API
bilibiliAI码农CC7/4/2026
Related Claims
UnverifiedLarge language models are typically released in two forms: Base Model and Instruction-tuned Model.80% similarUnverifiedLLM large model nodes configure instructions through Prompt Engineering, determining the role and style in which the model outputs content.77% similarUnverifiedThe architectural core of a multimodal large model must include a large language model (LLM) as its backbone.75% similarUnverifiedThe core difference between reasoning models and ordinary LLMs lies in the training approach rather than the architecture; reasoning models introduce a reinforcement learning stage on top of pretraining and supervised fine-tuning.75% similarUnverified大模型应用开发（LLM Application）偏向工程化落地，不需要从零推导Transformer数学公式或预训练百亿参数模型，而是调用、编排和微调已有大模型75% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/114069API
curl https://kongchang.com/api/v1/knowledge/claims/114069MCP
get_claim(id=114069)