|
{ |
|
"_name_or_path": "/content/xlm-roberta-base-ar-mafat-ner", |
|
"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": "U-ANG", |
|
"1": "L-ANG", |
|
"2": "B-ANG", |
|
"3": "I-ANG", |
|
"4": "U-DUC", |
|
"5": "I-DUC", |
|
"6": "L-DUC", |
|
"7": "B-DUC", |
|
"8": "I-EVE", |
|
"9": "L-EVE", |
|
"10": "B-EVE", |
|
"11": "U-EVE", |
|
"12": "L-FAC", |
|
"13": "U-FAC", |
|
"14": "I-FAC", |
|
"15": "B-FAC", |
|
"16": "L-GPE", |
|
"17": "B-GPE", |
|
"18": "I-GPE", |
|
"19": "U-GPE", |
|
"20": "U-INFORMAL", |
|
"21": "I-INFORMAL", |
|
"22": "L-INFORMAL", |
|
"23": "B-INFORMAL", |
|
"24": "U-LOC", |
|
"25": "I-LOC", |
|
"26": "L-LOC", |
|
"27": "B-LOC", |
|
"28": "I-MISC", |
|
"29": "U-MISC", |
|
"30": "B-MISC", |
|
"31": "L-MISC", |
|
"32": "O", |
|
"33": "I-ORG", |
|
"34": "L-ORG", |
|
"35": "U-ORG", |
|
"36": "B-ORG", |
|
"37": "L-PER", |
|
"38": "B-PER", |
|
"39": "I-PER", |
|
"40": "U-PER", |
|
"41": "I-TIMEX", |
|
"42": "L-TIMEX", |
|
"43": "U-TIMEX", |
|
"44": "B-TIMEX", |
|
"45": "U-TTL", |
|
"46": "L-TTL", |
|
"47": "B-TTL", |
|
"48": "I-TTL", |
|
"49": "B-WOA", |
|
"50": "L-WOA", |
|
"51": "U-WOA", |
|
"52": "I-WOA" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"B-ANG": 2, |
|
"B-DUC": 7, |
|
"B-EVE": 10, |
|
"B-FAC": 15, |
|
"B-GPE": 17, |
|
"B-INFORMAL": 23, |
|
"B-LOC": 27, |
|
"B-MISC": 30, |
|
"B-ORG": 36, |
|
"B-PER": 38, |
|
"B-TIMEX": 44, |
|
"B-TTL": 47, |
|
"B-WOA": 49, |
|
"I-ANG": 3, |
|
"I-DUC": 5, |
|
"I-EVE": 8, |
|
"I-FAC": 14, |
|
"I-GPE": 18, |
|
"I-INFORMAL": 21, |
|
"I-LOC": 25, |
|
"I-MISC": 28, |
|
"I-ORG": 33, |
|
"I-PER": 39, |
|
"I-TIMEX": 41, |
|
"I-TTL": 48, |
|
"I-WOA": 52, |
|
"L-ANG": 1, |
|
"L-DUC": 6, |
|
"L-EVE": 9, |
|
"L-FAC": 12, |
|
"L-GPE": 16, |
|
"L-INFORMAL": 22, |
|
"L-LOC": 26, |
|
"L-MISC": 31, |
|
"L-ORG": 34, |
|
"L-PER": 37, |
|
"L-TIMEX": 42, |
|
"L-TTL": 46, |
|
"L-WOA": 50, |
|
"O": 32, |
|
"U-ANG": 0, |
|
"U-DUC": 4, |
|
"U-EVE": 11, |
|
"U-FAC": 13, |
|
"U-GPE": 19, |
|
"U-INFORMAL": 20, |
|
"U-LOC": 24, |
|
"U-MISC": 29, |
|
"U-ORG": 35, |
|
"U-PER": 40, |
|
"U-TIMEX": 43, |
|
"U-TTL": 45, |
|
"U-WOA": 51 |
|
}, |
|
"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": "4.36.2", |
|
"type_vocab_size": 1, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"vocab_size": 250008 |
|
}, |
|
"entity_max_length": 150, |
|
"id2label": { |
|
"0": "O", |
|
"1": "ANG", |
|
"2": "DUC", |
|
"3": "EVE", |
|
"4": "FAC", |
|
"5": "GPE", |
|
"6": "INFORMAL", |
|
"7": "LOC", |
|
"8": "MISC", |
|
"9": "ORG", |
|
"10": "PER", |
|
"11": "TIMEX", |
|
"12": "TTL", |
|
"13": "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": 7, |
|
"25": 7, |
|
"26": 7, |
|
"27": 7, |
|
"28": 8, |
|
"29": 8, |
|
"30": 8, |
|
"31": 8, |
|
"32": 0, |
|
"33": 9, |
|
"34": 9, |
|
"35": 9, |
|
"36": 9, |
|
"37": 10, |
|
"38": 10, |
|
"39": 10, |
|
"40": 10, |
|
"41": 11, |
|
"42": 11, |
|
"43": 11, |
|
"44": 11, |
|
"45": 12, |
|
"46": 12, |
|
"47": 12, |
|
"48": 12, |
|
"49": 13, |
|
"50": 13, |
|
"51": 13, |
|
"52": 13 |
|
}, |
|
"label2id": { |
|
"ANG": 1, |
|
"DUC": 2, |
|
"EVE": 3, |
|
"FAC": 4, |
|
"GPE": 5, |
|
"INFORMAL": 6, |
|
"LOC": 7, |
|
"MISC": 8, |
|
"O": 0, |
|
"ORG": 9, |
|
"PER": 10, |
|
"TIMEX": 11, |
|
"TTL": 12, |
|
"WOA": 13 |
|
}, |
|
"marker_max_length": 128, |
|
"max_next_context": null, |
|
"max_prev_context": null, |
|
"model_max_length": null, |
|
"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 |
|
} |
|
|