Skip to main content
You can create datasets in three ways: upload a JSONL file, generate synthetic data, or import from Hugging Face. Choose the method that best fits your needs.

​
What Are Datasets?

A Dataset is a collection of datapoints that we will use to train a model how to respond to specific types of inputs. Understanding JSONL Datasets for Fine-Tuning A dataset for fine-tuning is a collection of examples in JSONL format (JSON Lines), where each line represents a single conversation example.

​
Dataset Structure

Each line in your JSONL file contains a JSON object with a single field called “messages”. This field holds an array of 3 message objects, each with:
  • A "role" field (identifying who is speaking)
  • A "content" field (containing the actual text)
The Three Roles
  • "system": Provides context and instructions that guide the model’s behavior
  • "user": Represents what a human user would say or ask
  • "assistant": Contains the ideal response you want the model to learn to generate
Example Format 
{"messages": [{"role": "system", "content": "You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided."}, {"role": "user", "content": "Title: No-Bake Nut Cookies\n\nIngredients: [\"1 c. firmly packed brown sugar\", \"1/2 c. evaporated milk\", \"1/2 tsp. vanilla\", \"1/2 c. broken nuts (pecans)\", \"2 Tbsp. butter or margarine\", \"3 1/2 c. bite size shredded rice biscuits\"]\n\nGeneric ingredients: "}, {"role": "assistant", "content": "[\"brown sugar\", \"milk\", \"vanilla\", \"nuts\", \"butter\", \"bite size shredded rice biscuits\"]"}]}
{"messages": [{"role": "system", "content": "You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided."}, {"role": "user", "content": "Title: Jewell Ball'S Chicken\n\nIngredients: [\"1 small jar chipped beef, cut up\", \"4 boned chicken breasts\", \"1 can cream of mushroom soup\", \"1 carton sour cream\"]\n\nGeneric ingredients: "}, {"role": "assistant", "content": "[\"beef\", \"chicken breasts\", \"cream of mushroom soup\", \"sour cream\"]"}]}
{"messages": [{"role": "system", "content": "You are a helpful recipe assistant. You are to extract the generic ingredients from each of the recipes provided."}, {"role": "user", "content": "Title: Creamy Corn\n\nIngredients: [\"2 (16 oz.) pkg. frozen corn\", \"1 (8 oz.) pkg. cream cheese, cubed\", \"1/3 c. butter, cubed\", \"1/2 tsp. garlic powder\", \"1/2 tsp. salt\", \"1/4 tsp. pepper\"]\n\nGeneric ingredients: "}, {"role": "assistant", "content": "[\"frozen corn\", \"cream cheese\", \"butter\", \"garlic powder\", \"salt\", \"pepper\"]"}]}
This format teaches the model that when given the system instruction to act as a customer service agent and asked about returns, it should respond with the specific return process information.

​
Create a Dataset

In Prem, you can create datasets in three ways:

Upload JSONL

Upload an existing dataset in JSONL format.

Generate Synthetic Data

Generate datasets from files, videos, or websites.

Import from Hugging Face

Import datasets from Hugging Face using templates.

​
Do More With Datasets

Create a Snapshot

Save a snapshot of your dataset.

Enrich a Dataset

Enrich your dataset with additional synthetic data.

Autosplit a Dataset

Automatically split your dataset into training, validation, and test sets.