Large language model

Generative AI based on the Transformer architecture, with input and output modalities that include text. It became widely known to the public through ChatGPT.

Major models

• OpenAI’s GPT
• Anthropic’s Claude
• Google’s Gemini
• Meta’s Llama
• Alibaba’s Qwen
• Model database: models.dev/

Articles

• 2024-11-21 - Re-Invoke: Tool invocation rewriting for zero-shot tool retrieval
• 2024-08-14 - LLMs develop their own understanding of reality as their language abilities improve
• 2023-12-11 - Why We Support and Encourage the Use of Large Language Models in NEJM AI Submissions | NEJM AI

See also

• ML crash course - LLM
• LLM token sampling
• Free LLMs

External links

• applied-llms.org/ - What We’ve Learned From A Year of Building with LLMs
• LLM Engineer’s Almanac