Downloads · 30 days
0
laya-typed-decisions
huanggengwei/laya-typed-decisions
laya-typed-decisions is a machine learning model from huanggengwei. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is Laya fine-tuned on the 1,200 training cases (6,000 decisions) of the independent LocalLLaMA/typed-decisions benchmark.
Access
Public
Updated Sep 23, 2026
Parameters
421M
843 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.7 GB · 100%
At a glance
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026
- SHA
- 14cc9a5e
Model card
From the Hugging Face model README
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 0.783 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 | 0.783 | 0.509 | 0.064 | 0.229 | 0.229 | 0.994 | 157.8 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("huanggengwei/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. Fine-tuned from Convai Innovations' Laya.
- Library
- transformers
- License
- apache-2.0
- Created
- Sep 23, 2026
- Updated
- Sep 23, 2026