File size: 1,542 Bytes
0d94bea |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 |
{
"_num_labels": 5,
"architectures": [
"AlbertModel"
],
"attention_probs_dropout_prob": 0,
"bad_words_ids": null,
"bos_token_id": 2,
"classifier_dropout_prob": 0.1,
"decoder_start_token_id": null,
"do_sample": false,
"down_scale_factor": 1,
"early_stopping": false,
"embedding_size": 128,
"eos_token_id": 3,
"finetuning_task": null,
"gap_size": 0,
"hidden_act": "gelu",
"hidden_dropout_prob": 0,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2",
"3": "LABEL_3",
"4": "LABEL_4"
},
"initializer_range": 0.02,
"inner_group_num": 1,
"intermediate_size": 3072,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2,
"LABEL_3": 3,
"LABEL_4": 4
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "albert",
"net_structure_type": 0,
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beams": 1,
"num_hidden_groups": 1,
"num_hidden_layers": 12,
"num_memory_blocks": 0,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"pad_token_id": 0,
"prefix": null,
"pruned_heads": {},
"repetition_penalty": 1.0,
"task_specific_params": null,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"use_bfloat16": false,
"vocab_size": 30000
}
|