akshatbindal/laya-typed-decisions

Laya (Fine-Tuned on Typed-Decisions Benchmark)

This is Laya fine-tuned on the 1,200 training cases (6,000 decisions) of the independent LocalLLaMA/typed-decisions benchmark.

On the official 400-case test set (2,000 decisions across Agent Trace Observability, Customer Service, Invoice Processing, and Security Incidents), it achieves 0.757 Accuracy, outperforming TypeSafe Jev 1.13.0 (0.727) and surpassing the benchmark's Teacher Self-Agreement ceiling (0.735).

Head-to-Head Benchmark Results

Model	Kind	Accuracy	Soft Acc	Brier Score	ECE	Score MAE	Within 1 Level	Latency (p50)	Cost/Case
Laya (Ours)	fine-tuned	0.757	0.507	0.069	0.209	0.260	0.990	146.1 ms	$0.00 (Self-Hosted)
TypeSafe Jev 1.13.0	general	0.727	0.580	0.148	0.144	0.391	0.952	710 ms	$0.0004 (API)
ModernBERT-base (149M)	specialist	0.646	0.542	0.119	0.179	0.444	0.931	349 ms	$0.00
Teacher Self-Agreement	ceiling	0.735	-	-	-	-	-	-	-

Installation & Quickstart

pip install laya

import laya

# Load the fine-tuned model directly from Hugging Face
agent = laya.load("convaiinnovations/laya-typed-decisions")

# Evaluate any workflow state and typed questions in a single forward pass
result = agent.predict(state, questions)
print(result["answers"])

License

Apache 2.0. Developed by Convai Innovations.