Fine-tuning - OpenAI API
platform.openai.com · 1,098 words · saved by 1 readers
An API for accessing new AI models developed by OpenAI
LLM output is non-deterministic, and model behavior changes between model snapshots and families. Developers must constantly measure and tune the performance of LLM applications to ensure they’re getting the best results. In this guide, we explore the techniques and OpenAI platform tools you can use to ensure high quality outputs from the model. This guide covers evals and fine-tuning workflows that are being moved into legacy documentation. See the deprecations page for the current timelines for the affected platform surfaces. Evals Systematically measure performance. Prompt engineering Give
saved by
related reading
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- The Shape of AI | UX Patterns for Artificial Intelligence Designshapeof.ai
- Together AI | The AI Native Cloudtogether.ai
- GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- PromptLayer — Prompt Management, Evals & Observabilitypromptlayer.com
- Replicate - Run AI with an APIreplicate.com
- Goodfire AIgoodfire.ai
- Hugging Face – The AI community building the future.huggingface.co
- Cookbookcookbook.openai.com
- Tinkerthinkingmachines.ai