amberlin-trainstation
MeasurementWhere the model behind Amberlin's tool calling is chosen and measured. The current phase trains nothing, on purpose: a small model under a grammar already scores 114 of 119 held-out questions.
LoRA, a way to fine-tune a model by training a small set of added weights.
Where the model behind Amberlin's tool calling is chosen and measured. The current phase trains nothing, on purpose: a small model under a grammar already scores 114 of 119 held-out questions.