Update config.json
Browse files- config.json +0 -29
config.json
CHANGED
|
@@ -1,55 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"_num_labels": 2,
|
| 3 |
"architectures": [
|
| 4 |
"AlbertModel"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"bos_token_id": 2,
|
| 8 |
"classifier_dropout_prob": 0.1,
|
| 9 |
-
"do_sample": false,
|
| 10 |
-
"early_stopping": false,
|
| 11 |
"embedding_size": 128,
|
| 12 |
"eos_token_id": 3,
|
| 13 |
-
"finetuning_task": null,
|
| 14 |
"hidden_act": "gelu_new",
|
| 15 |
"hidden_dropout_prob": 0.1,
|
| 16 |
"hidden_size": 256,
|
| 17 |
-
"id2label": {
|
| 18 |
-
"0": "LABEL_0",
|
| 19 |
-
"1": "LABEL_1"
|
| 20 |
-
},
|
| 21 |
"initializer_range": 0.02,
|
| 22 |
"inner_group_num": 1,
|
| 23 |
"intermediate_size": 1024,
|
| 24 |
-
"is_decoder": false,
|
| 25 |
-
"is_encoder_decoder": false,
|
| 26 |
-
"label2id": {
|
| 27 |
-
"LABEL_0": 0,
|
| 28 |
-
"LABEL_1": 1
|
| 29 |
-
},
|
| 30 |
"layer_norm_eps": 1e-12,
|
| 31 |
-
"length_penalty": 1.0,
|
| 32 |
-
"max_length": 20,
|
| 33 |
"max_position_embeddings": 128,
|
| 34 |
-
"min_length": 0,
|
| 35 |
"model_type": "albert",
|
| 36 |
-
"no_repeat_ngram_size": 0,
|
| 37 |
"num_attention_heads": 4,
|
| 38 |
-
"num_beams": 1,
|
| 39 |
"num_hidden_groups": 1,
|
| 40 |
"num_hidden_layers": 12,
|
| 41 |
-
"num_return_sequences": 1,
|
| 42 |
-
"output_attentions": false,
|
| 43 |
-
"output_hidden_states": false,
|
| 44 |
"output_past": true,
|
| 45 |
"pad_token_id": 0,
|
| 46 |
-
"pruned_heads": {},
|
| 47 |
-
"repetition_penalty": 1.0,
|
| 48 |
-
"temperature": 1.0,
|
| 49 |
-
"top_k": 50,
|
| 50 |
-
"top_p": 1.0,
|
| 51 |
-
"torchscript": false,
|
| 52 |
"type_vocab_size": 2,
|
| 53 |
-
"use_bfloat16": false,
|
| 54 |
"vocab_size": 30522
|
| 55 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"AlbertModel"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
"bos_token_id": 2,
|
| 7 |
"classifier_dropout_prob": 0.1,
|
|
|
|
|
|
|
| 8 |
"embedding_size": 128,
|
| 9 |
"eos_token_id": 3,
|
|
|
|
| 10 |
"hidden_act": "gelu_new",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 256,
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
"inner_group_num": 1,
|
| 15 |
"intermediate_size": 1024,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
"layer_norm_eps": 1e-12,
|
|
|
|
|
|
|
| 17 |
"max_position_embeddings": 128,
|
|
|
|
| 18 |
"model_type": "albert",
|
|
|
|
| 19 |
"num_attention_heads": 4,
|
|
|
|
| 20 |
"num_hidden_groups": 1,
|
| 21 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
|
|
|
| 22 |
"output_past": true,
|
| 23 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"type_vocab_size": 2,
|
|
|
|
| 25 |
"vocab_size": 30522
|
| 26 |
}
|