distilbert-squad-qa / config.json
HariomSahu's picture
Training run v20250726_220146 - F1: 84.5969, EM: 76.2725
052be9c verified
raw
history blame
515 Bytes
{
"activation": "gelu",
"architectures": [
"DistilBertForQuestionAnswering"
],
"attention_dropout": 0.1,
"dim": 768,
"dropout": 0.1,
"hidden_dim": 3072,
"initializer_range": 0.02,
"max_position_embeddings": 512,
"model_type": "distilbert",
"n_heads": 12,
"n_layers": 6,
"pad_token_id": 0,
"qa_dropout": 0.1,
"seq_classif_dropout": 0.2,
"sinusoidal_pos_embds": false,
"tie_weights_": true,
"torch_dtype": "float32",
"transformers_version": "4.54.0",
"vocab_size": 30522
}