✨ Datafast - NEW! ✨
A convenient way to create datasets
Learn how to create text classification datasets with Datafast.
Visit the Datafast GitHub repository for more information and resources.
How to use LLMs as a beginner
Work in progress, more guides coming...
Quick start guide to implementing OpenAI Chat models in your project.
A brief intro to using Anthropic’s Claude for chat or text completions.
Learn how to integrate Google’s Gemini into your workflow.
Structured Output
Work in progress, more guides coming...
Generate structured JSON or XML responses using OpenAI’s chat models.
Harness Anthropic’s Claude for structured data generation.
Leverage Google’s Gemini for consistent, structured outputs.
LLM Dataset Creation
Work in progress, more guides coming...
Create a quick question-generating pipeline using Distilabel + OpenAI.
Build your own text generation pipeline with the Genstruct7B model.
Create a self-instruct pipeline using Distilabel + OpenAI.
We use the FREE Gemini API, an exisiting dataset of person, and dynamic prompts to generate a diverse dataset and publish it to your huggingface hub.
The most relevant pieces of the Hugging Face Datasets library documentation, with a focus on text data handling and processing.
LLM Evaluation
Work in progress, more guides coming...
Automated Metrics
Intro to basic metrics for evaluating language model outputs.
Dataset Creation and Filtering
Learn how to create and filter datasets for your specific needs
Learn how to filter existing datasets to kickstart domain-specific projects.