wietsedv's picture
model dump
e2cb82a
raw
history blame
1.37 kB
{
"_name_or_path": "output/xlm-roberta-base_ft_udpos28-got/1d6ca3e8",
"architectures": [
"XLMRobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "ADJ",
"1": "ADP",
"2": "ADV",
"3": "AUX",
"4": "CCONJ",
"5": "DET",
"6": "INTJ",
"7": "NOUN",
"8": "NUM",
"9": "PART",
"10": "PRON",
"11": "PROPN",
"12": "PUNCT",
"13": "SCONJ",
"14": "SYM",
"15": "VERB",
"16": "X"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ADJ": 0,
"ADP": 1,
"ADV": 2,
"AUX": 3,
"CCONJ": 4,
"DET": 5,
"INTJ": 6,
"NOUN": 7,
"NUM": 8,
"PART": 9,
"PRON": 10,
"PROPN": 11,
"PUNCT": 12,
"SCONJ": 13,
"SYM": 14,
"VERB": 15,
"X": 16
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.10.2",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}