imvladikon's picture
iahlt/span-marker-xlm-roberta-base-nemo-mt-he
a12a6ae
{
"architectures": [
"SpanMarkerModel"
],
"encoder": {
"_name_or_path": "xlm-roberta-base",
"add_cross_attention": false,
"architectures": [
"XLMRobertaForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"cross_attention_hidden_size": null,
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "S-ANG",
"1": "B-ANG",
"2": "I-ANG",
"3": "E-ANG",
"4": "S-DUC",
"5": "B-DUC",
"6": "I-DUC",
"7": "E-DUC",
"8": "B-EVE",
"9": "E-EVE",
"10": "S-EVE",
"11": "I-EVE",
"12": "S-FAC",
"13": "B-FAC",
"14": "E-FAC",
"15": "I-FAC",
"16": "S-GPE",
"17": "B-GPE",
"18": "E-GPE",
"19": "I-GPE",
"20": "S-LOC",
"21": "B-LOC",
"22": "E-LOC",
"23": "I-LOC",
"24": "O",
"25": "S-ORG",
"26": "B-ORG",
"27": "E-ORG",
"28": "I-ORG",
"29": "B-PER",
"30": "I-PER",
"31": "E-PER",
"32": "S-PER",
"33": "B-WOA",
"34": "E-WOA",
"35": "I-WOA",
"36": "S-WOA"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"B-ANG": 1,
"B-DUC": 5,
"B-EVE": 8,
"B-FAC": 13,
"B-GPE": 17,
"B-LOC": 21,
"B-ORG": 26,
"B-PER": 29,
"B-WOA": 33,
"E-ANG": 3,
"E-DUC": 7,
"E-EVE": 9,
"E-FAC": 14,
"E-GPE": 18,
"E-LOC": 22,
"E-ORG": 27,
"E-PER": 31,
"E-WOA": 34,
"I-ANG": 2,
"I-DUC": 6,
"I-EVE": 11,
"I-FAC": 15,
"I-GPE": 19,
"I-LOC": 23,
"I-ORG": 28,
"I-PER": 30,
"I-WOA": 35,
"O": 24,
"S-ANG": 0,
"S-DUC": 4,
"S-EVE": 10,
"S-FAC": 12,
"S-GPE": 16,
"S-LOC": 20,
"S-ORG": 25,
"S-PER": 32,
"S-WOA": 36
},
"layer_norm_eps": 1e-05,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 514,
"min_length": 0,
"model_type": "xlm-roberta",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"output_scores": false,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"prefix": null,
"problem_type": null,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"return_dict": true,
"return_dict_in_generate": false,
"sep_token_id": null,
"suppress_tokens": null,
"task_specific_params": null,
"temperature": 1.0,
"tf_legacy_loss": false,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": null,
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.35.2",
"type_vocab_size": 1,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 250008
},
"entity_max_length": 100,
"id2label": {
"0": "O",
"1": "ANG",
"2": "DUC",
"3": "EVE",
"4": "FAC",
"5": "GPE",
"6": "LOC",
"7": "ORG",
"8": "PER",
"9": "WOA"
},
"id2reduced_id": {
"0": 1,
"1": 1,
"2": 1,
"3": 1,
"4": 2,
"5": 2,
"6": 2,
"7": 2,
"8": 3,
"9": 3,
"10": 3,
"11": 3,
"12": 4,
"13": 4,
"14": 4,
"15": 4,
"16": 5,
"17": 5,
"18": 5,
"19": 5,
"20": 6,
"21": 6,
"22": 6,
"23": 6,
"24": 0,
"25": 7,
"26": 7,
"27": 7,
"28": 7,
"29": 8,
"30": 8,
"31": 8,
"32": 8,
"33": 9,
"34": 9,
"35": 9,
"36": 9
},
"label2id": {
"ANG": 1,
"DUC": 2,
"EVE": 3,
"FAC": 4,
"GPE": 5,
"LOC": 6,
"O": 0,
"ORG": 7,
"PER": 8,
"WOA": 9
},
"marker_max_length": 128,
"max_next_context": null,
"max_prev_context": null,
"model_max_length": 512,
"model_max_length_default": 512,
"model_type": "span-marker",
"span_marker_version": "1.5.0",
"torch_dtype": "float32",
"trained_with_document_context": false,
"transformers_version": "4.35.2",
"vocab_size": 250008
}