YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Valence–Arousal Regression (Embeddings → VA)
This repo contains a PyTorch regression model that predicts Valence and Arousal (1–9 scale) from embedding vectors.
Files
best_va_model_r2.pt: model weights + configx_scaler.pkl: input scaler (StandardScaler)y_scaler.pkl: target scaler (StandardScaler)meta.json: loading + feature order details
Input
Concatenate in this order:
[CLS | MAX_POOL | AVG_POOL]
Scale inputs using x_scaler.pkl.
Output
Model outputs scaled VA, then inverse-transform using y_scaler.pkl to get final VA (1–9).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support