evalatin2022-pos-open / config.json
djstrong's picture
init
5974883
raw
history blame
1.38 kB
{
"_name_or_path": "model_bin_xlmroberta_xlm-roberta-large_1647708620.7398984/best_model/",
"architectures": [
"XLMRobertaForTokenClassification"
],
"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": 1024,
"id2label": {
"0": "",
"1": "ADJ",
"2": "ADP",
"3": "ADV",
"4": "AUX",
"5": "CCONJ",
"6": "DET",
"7": "INTJ",
"8": "NOUN",
"9": "NUM",
"10": "PART",
"11": "PRON",
"12": "PROPN",
"13": "PUNCT",
"14": "SCONJ",
"15": "VERB",
"16": "X",
"17": "O"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"": 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,
"VERB": 15,
"X": 16,
"O": 17
},
"layer_norm_eps": 1e-05,
"max_position_embeddings": 514,
"model_type": "xlm-roberta",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"output_past": true,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.13.0",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 250002
}