Skip to content
ModelListedExternal
Download

VAE Banking77 OpenIntentClassification

This is a Variational Autoencoder (VAE) trained on the PolyAI/banking77 dataset.

Sourcehuggingface.co/KaiquanMah/VAE-Banking77-OpenIntentClassification/tree/72e34d7a71ad826906c8a6d9a9fb3dc505652f21
KindVAEVersionvae_best_state_dictCgrade

Model source

Kind
VAE
File size
1.70 MB
Version
vvae_best_state_dict
Updated
Oct 20, 2026
Downloads
13
Source
Hugging Face

Source description

VAE trained on Banking 77 Open Intent Classification Dataset

This is a Variational Autoencoder (VAE) trained on the PolyAI/banking77 dataset.

Architecture

  • input_dim: 768
  • hidden_dim: 256
  • latent_dim: 64

Encoder

The encoder maps the input to a latent space distribution.

encoder = nn.Sequential(
            nn.Linear(input_dim, hidden_dim),
            nn.ReLU()
        )

mu = nn.Linear(hidden_dim, latent_dim)
logvar = nn.Linear(hidden_dim, latent_dim)

Decoder

The decoder reconstructs the input from a sample of the latent space.

decoder = nn.Sequential(
            nn.Linear(latent_dim, hidden_dim),
            nn.ReLU(),
            nn.Linear(hidden_dim, input_dim)
        )

Metrics

The model was trained and evaluated using the following metrics:

  1. Training set: VAE Loss
    • 50% reconstruction loss between original input vs reconstructed output
    • 50% KL divergence between Latent Z vs standard normal distribution
  2. Validation set: 100% reconstruction loss -> used to find the best model (with the lowest reconstruction loss)

Sources

1 source
Hugging FacePrimaryVersion 72e34d7a71ad826906c8a6d9a9fb3dc505652f21
huggingface.co/KaiquanMah/VAE-Banking77-OpenIntentClassification/tree/72e34d7a71ad826906c8a6d9a9fb3dc505652f21

Verified Oct 20

Model artifacts

1 artifact

vae_best_state_dict.pt

pt · 1.70 MB · SHA-256 2952aec3b69f…30f4 · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeAug 3huggingface.co/KaiquanMah/VAE-Banking77-OpenIntentClassification

--- license: mit datasets: - PolyAI/banking77 language: - en tags: - autoencoder --- # VAE trained on Banking 77 Open Intent Classification Dataset This is a Variational Autoencoder (VAE) trained on the [PolyAI/banking77](https://huggingface.co/datasets/PolyAI/banking77) dataset. ### Architecture - **input_dim**: 768 - **hidden_dim**: 256 - **latent_dim**: 64 #### Encoder The encoder maps the input to a latent space distribution. ```python encoder = nn.Sequential( nn.Linear(input_dim, hidden_dim), nn.ReLU() ) mu = nn.Linear(hidden_dim, latent_dim) logvar = nn.Linear(hidden_dim, latent_dim) ``` #### Decoder The decoder reconstructs the input from a sample of the latent space. ```python decoder = nn.Sequential( nn.Linear(latent_dim, hidden_dim), nn.ReLU(), nn.Linear(hidden_dim, input_dim) ) ``` #### Metrics The model was trained and evaluated using the following metrics: 1. Training set: VAE Loss * 50% reconstruction loss between original input vs reconstructed output * 50% KL divergence between Latent Z vs standard normal distribution 2. Validation set: 100% reconstruction loss -> used to find the best model (with the lowest reconstruction loss)

NoteOct 20huggingface.co/KaiquanMah/VAE-Banking77-OpenIntentClassification

Source context: 13 downloads · 0 likes · Repo KaiquanMah/VAE-Banking77-OpenIntentClassification

NoteAug 3huggingface.co/KaiquanMah/VAE-Banking77-OpenIntentClassification

Source context: 5 downloads · 0 likes · Repo KaiquanMah/VAE-Banking77-OpenIntentClassification