madhurjindal/autonlp-Gibberish-Detector-492513457

Partial fine-tune vs distilbert/distilbert-base-uncased. Partial change: 64% of the weights changed (attention, embeddings, mlp, norms), in 6 of 6 layers.

Tensors changed: Embeddings 2/4, Attention 48/48, MLP 24/24, Norms 24/24

1 derivatives checked

3 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse