alpamayo1-5-sft

What problem does it solve?

This Skill automates the end-to-end process of fine-tuning the Alpamayo-1.5 VLM action model on PAI (with navigation conditioning) or LingoQA (for visual question answering), reducing the time and complexity of training and fine-tuning custom agents.

Core Features & Use Cases

• PAI Navigation Conditioning: Fine-tune the model for trajectory prediction guided by route instructions.
• LingoQA Visual Question Answering: Fine-tune the model for driving scene question answering.
• End-to-End Pipeline: Automates the entire process, from downloading checkpoints and datasets to training and evaluation.
• Use Case: A developer wants to fine-tune the Alpamayo-1.5 model for a navigation-based autonomous vehicle application. The developer uses this Skill to train the model on the PAI dataset with navigation conditioning and evaluate the results.

Quick Start

Run the 'alpamayo1-5-sft' skill to fine-tune the Alpamayo-1.5 model on PAI for navigation conditioning. Provide the necessary paths to the PAI dataset, navigation annotations, and Alpamayo-1.5 checkpoint.