Update config.json
Browse files- config.json +36 -0
config.json
CHANGED
@@ -1,28 +1,64 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"attention_probs_dropout_prob": 0,
|
|
|
3 |
"bos_token_id": 2,
|
4 |
"classifier_dropout_prob": 0.1,
|
|
|
|
|
5 |
"down_scale_factor": 1,
|
|
|
6 |
"embedding_size": 128,
|
7 |
"eos_token_id": 3,
|
|
|
8 |
"gap_size": 0,
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0,
|
11 |
"hidden_size": 4096,
|
|
|
|
|
|
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"inner_group_num": 1,
|
14 |
"intermediate_size": 16384,
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
"layer_norm_eps": 1e-12,
|
16 |
"layers_to_keep": [],
|
|
|
|
|
17 |
"max_position_embeddings": 512,
|
|
|
18 |
"model_type": "albert",
|
19 |
"net_structure_type": 0,
|
|
|
20 |
"num_attention_heads": 64,
|
|
|
21 |
"num_hidden_groups": 1,
|
22 |
"num_hidden_layers": 12,
|
23 |
"num_memory_blocks": 0,
|
|
|
|
|
|
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
"type_vocab_size": 2,
|
|
|
27 |
"vocab_size": 30000
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"_num_labels": 2,
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForQuestionAnswering"
|
5 |
+
],
|
6 |
"attention_probs_dropout_prob": 0,
|
7 |
+
"bad_words_ids": null,
|
8 |
"bos_token_id": 2,
|
9 |
"classifier_dropout_prob": 0.1,
|
10 |
+
"decoder_start_token_id": null,
|
11 |
+
"do_sample": false,
|
12 |
"down_scale_factor": 1,
|
13 |
+
"early_stopping": false,
|
14 |
"embedding_size": 128,
|
15 |
"eos_token_id": 3,
|
16 |
+
"finetuning_task": null,
|
17 |
"gap_size": 0,
|
18 |
"hidden_act": "gelu",
|
19 |
"hidden_dropout_prob": 0,
|
20 |
"hidden_size": 4096,
|
21 |
+
"id2label": {
|
22 |
+
"0": "LABEL_0",
|
23 |
+
"1": "LABEL_1"
|
24 |
+
},
|
25 |
"initializer_range": 0.02,
|
26 |
"inner_group_num": 1,
|
27 |
"intermediate_size": 16384,
|
28 |
+
"is_decoder": false,
|
29 |
+
"is_encoder_decoder": false,
|
30 |
+
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1
|
33 |
+
},
|
34 |
"layer_norm_eps": 1e-12,
|
35 |
"layers_to_keep": [],
|
36 |
+
"length_penalty": 1.0,
|
37 |
+
"max_length": 20,
|
38 |
"max_position_embeddings": 512,
|
39 |
+
"min_length": 0,
|
40 |
"model_type": "albert",
|
41 |
"net_structure_type": 0,
|
42 |
+
"no_repeat_ngram_size": 0,
|
43 |
"num_attention_heads": 64,
|
44 |
+
"num_beams": 1,
|
45 |
"num_hidden_groups": 1,
|
46 |
"num_hidden_layers": 12,
|
47 |
"num_memory_blocks": 0,
|
48 |
+
"num_return_sequences": 1,
|
49 |
+
"output_attentions": false,
|
50 |
+
"output_hidden_states": false,
|
51 |
"output_past": true,
|
52 |
"pad_token_id": 0,
|
53 |
+
"prefix": null,
|
54 |
+
"pruned_heads": {},
|
55 |
+
"repetition_penalty": 1.0,
|
56 |
+
"task_specific_params": null,
|
57 |
+
"temperature": 1.0,
|
58 |
+
"top_k": 50,
|
59 |
+
"top_p": 1.0,
|
60 |
+
"torchscript": false,
|
61 |
"type_vocab_size": 2,
|
62 |
+
"use_bfloat16": false,
|
63 |
"vocab_size": 30000
|
64 |
}
|