laya-vn

Fine-tuned Laya decision model for the Korean visual-novel prototype 재의 λ°±μž‘ (The Count of Ashes). It judges a line the player typed against the scene and the listener's need, in one forward pass, and answers three questions:

  • impact β€” 5-level score (0 deeply hurts … 4 exactly what they needed)
  • vengeance β€” how much the line leans toward revenge
  • nonsense β€” joke / abuse / off-topic input

The game turns these into affection changes and ending conditions.

Usage

import laya
agent = laya.load("ringwring/laya-vn")  # or a local snapshot_download path
# state / questions: see server/laya_prompt.py (build_state, QUESTIONS)
answers = agent.predict(state, QUESTIONS)["answers"]

Training & evaluation

RLCD fine-tuning on ~2,000 soft-labelled Korean lines (18 in-game events). Trained on batch A, evaluated on an unseen batch B (900 lines) written by a different labeller:

zero-shot laya-multilingual laya-vn
reaction tier accuracy (low/mid/high) 31.9% 68.8%
impact expected-value MAE (0–4) 1.09 0.52
impact within Β±1 level 68% 92%
vengeance MAE 0.44 0.12
nonsense MAE 0.35 0.04

The released weights were retrained on A+B (6 epochs, ~8 min on an RTX 5080). The model is specific to this game's events and prompt format; it is not a general dialogue classifier.

Downloads last month
-
Safetensors
Model size
0.3B params
Tensor type
F16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for ringwring/laya-vn

Finetuned
(93)
this model