Max Caldwell
Fine-tuning a small model to drive Nushell
LFM3 1.7B goes from 8% to 92.6% correct Nushell tool calls with a LoRA and data generated from scratch.
script<T>
Scriptt is prompting with a model for types to catch agent errors early.
LFM3 1.7B goes from 8% to 92.6% correct Nushell tool calls with a LoRA and data generated from scratch.
Scriptt is prompting with a model for types to catch agent errors early.