BeaverYard

BeaverYard

AI Fine-Tuning Platform

Examples

Sanitized examples showing how teams structure datasets for fine-tuning runs.

These examples are sanitized. Validation runs before payment; if validation fails, you won't be charged.

Customer Support Tone Adapter

Use case:
Consistent, empathetic replies across support channels with clear escalation boundaries.
Dataset format:
TXT dialogue pairs (customer message → approved response), tagged by scenario and escalation policy.
Validation checks:
File format and structure, dataset size and tier caps (MB and tokens), required fields, and policy-safe content.
Expected outcome:
More consistent tone and fewer unnecessary escalations.
Dataset formatPlan limitsValidation rules

Product Q&A Bot

Use case:
Accurate answers to repetitive product questions with technical precision.
Dataset format:
JSONL prompt/answer records, each grounded to canonical product documentation sources.
Validation checks:
JSONL validity, required fields, dataset MB and token caps per plan, and minimum quality and consistency checks.
Expected outcome:
Higher first-response accuracy in self-serve channels.
Dataset formatPlan limitsValidation rules

Structured Data Extraction

Use case:
Reliable extraction from semi-structured text into a stable schema for automation.
Dataset format:
CSV (input text → structured output fields) aligned to a single extraction schema.
Validation checks:
CSV structure, schema consistency, dataset MB and token caps per plan, and per-record limits.
Expected outcome:
Cleaner downstream automation with less manual cleanup.
Dataset formatPlan limitsValidation rules
Start a runRead validation rules first
Start Run