|
{ |
|
"architectures": [ |
|
"AlbertForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0, |
|
"bos_token_id": 2, |
|
"classifier_dropout_prob": 0.1, |
|
"down_scale_factor": 1, |
|
"embedding_size": 128, |
|
"eos_token_id": 3, |
|
"finetuning_task": "persiannews", |
|
"gap_size": 0, |
|
"hidden_act": "gelu_new", |
|
"hidden_dropout_prob": 0, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "\u0627\u062c\u062a\u0645\u0627\u0639\u06cc", |
|
"1": "\u0627\u0642\u062a\u0635\u0627\u062f\u06cc", |
|
"2": "\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644", |
|
"3": "\u0633\u06cc\u0627\u0633\u06cc", |
|
"4": "\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc", |
|
"5": "\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc", |
|
"6": "\u0648\u0631\u0632\u0634\u06cc", |
|
"7": "\u067e\u0632\u0634\u06a9\u06cc" |
|
}, |
|
"initializer_range": 0.02, |
|
"inner_group_num": 1, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"\u0627\u062c\u062a\u0645\u0627\u0639\u06cc": 0, |
|
"\u0627\u0642\u062a\u0635\u0627\u062f\u06cc": 1, |
|
"\u0628\u06cc\u0646 \u0627\u0644\u0645\u0644\u0644": 2, |
|
"\u0633\u06cc\u0627\u0633\u06cc": 3, |
|
"\u0639\u0644\u0645\u06cc \u0641\u0646\u0627\u0648\u0631\u06cc": 4, |
|
"\u0641\u0631\u0647\u0646\u06af\u06cc \u0647\u0646\u0631\u06cc": 5, |
|
"\u0648\u0631\u0632\u0634\u06cc": 6, |
|
"\u067e\u0632\u0634\u06a9\u06cc": 7 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "albert", |
|
"net_structure_type": 0, |
|
"num_attention_heads": 12, |
|
"num_hidden_groups": 1, |
|
"num_hidden_layers": 12, |
|
"num_memory_blocks": 0, |
|
"pad_token_id": 0, |
|
"type_vocab_size": 2, |
|
"vocab_size": 80000 |
|
} |
|
|