:rocket: Get Start With Prompt Engineering
LLMs: Large Language Models
Totally , it can be seen as two types of LLMs:Base LLM Predicts next word, based on text training data.
&
Instruction Tuned LLM Tries to follow instructions, Fine-tune on instructions and good attempts at following those instructions.
🍏 Principles * should follow when Prompting
- 1️⃣ Write clear and specific instructions
- Tactic 1 : Use delimiters like `Triple quotes` , `Triple backticks` , `Triple dashes` , `Angle brackets` , `XML tags` ... - Tactic 2 : Ask for structured output like `HTML` , `JSON` ... - Tactic 3 : Check whether conditions are satisfied. Check assumptions required to do the task. - Tactic 4 : Few-shot prompting : `Give successful examples of completing tasks` then ask model to perform the task.
评论