⛺️ Cheat Sheet: Mastering Temperature and Top_p in ChatGPT API (a few tips and tricks on controlling the creativity/deterministic output of prompt responses.) - API - OpenAI Developer Forum
Hello everyone! Ok, I admit had help from OpenAi with this. But what I “helped” put together I think can greatly improve the results and costs of using OpenAi within your apps and plugins, specially for those looking to guide internal prompts for plugins… @ruv I’d like to introduce you to two important parameters that you can use with OpenAI’s GPT API to help control text generation behavior: temperature and top_p sampling. These parameters are especially useful when working with GPT for tas...
April 22, 2023, 4:09am 1 Hello everyone! Ok, I admit had help from OpenAi with this. But what I “helped” put together I think can greatly improve the results and costs of using OpenAi within your apps and plugins, specially for those looking to guide internal prompts for plugins… @ruv I’d like to introduce you to two important parameters that you can use with OpenAI’s GPT API to help control text generation behavior: temperature and top_p sampling. These parameters are especially useful when working with GPT for tasks such as code generation, creative writing, chatbot responses, and…
related reading
- LLM Settings | Prompt Engineering Guidepromptingguide.ai
- Prompt engineering | OpenAI APIplatform.openai.com
- Defeating Nondeterminism in LLM Inference - Thinking Machines Labthinkingmachines.ai
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- Non-determinism in GPT-4 is caused by Sparse MoE - 152334H152334h.github.io
- LLM Samplers Explained · GitHubgist.github.com
- GPT in 60 Lines of NumPy | Jay Modyjaykmody.com
- gpt-4.pdfcdn.openai.com
- Prompt generation | OpenAI APIplatform.openai.com
- Text generation | OpenAI APIplatform.openai.com
- microgptkarpathy.github.io
- Late Takes on OpenAI o1alexirpan.com