|
{
|
|
"_name_or_path": "osiria/minilm-l12-h384-italian-cross-encoder",
|
|
"architectures": [
|
|
"XLMRobertaForSequenceClassification"
|
|
],
|
|
"attention_probs_dropout_prob": 0.1,
|
|
"bos_token_id": 0,
|
|
"classifier_dropout": null,
|
|
"eos_token_id": 2,
|
|
"hidden_act": "gelu",
|
|
"hidden_dropout_prob": 0.1,
|
|
"hidden_size": 384,
|
|
"id2label": {
|
|
"0": "LABEL_0"
|
|
},
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 1536,
|
|
"label2id": {
|
|
"LABEL_0": 0
|
|
},
|
|
"layer_norm_eps": 1e-05,
|
|
"max_position_embeddings": 514,
|
|
"model_type": "xlm-roberta",
|
|
"num_attention_heads": 12,
|
|
"num_hidden_layers": 12,
|
|
"pad_token_id": 1,
|
|
"position_embedding_type": "absolute",
|
|
"torch_dtype": "float32",
|
|
"transformers_version": "4.46.2",
|
|
"type_vocab_size": 1,
|
|
"use_cache": true,
|
|
"vocab_size": 30498
|
|
}
|
|
|