Update config.json
Browse files- config.json +10 -18
config.json
CHANGED
@@ -1,11 +1,15 @@
|
|
1 |
{
|
|
|
2 |
"activation_dropout": 0.0,
|
|
|
|
|
3 |
"architectures": [
|
4 |
"BartModel",
|
5 |
"BartForMaskedLM",
|
6 |
"BartForSequenceClassification"
|
7 |
],
|
8 |
"attention_dropout": 0.0,
|
|
|
9 |
"classif_dropout": 0.0,
|
10 |
"d_model": 1024,
|
11 |
"decoder_attention_heads": 16,
|
@@ -13,39 +17,32 @@
|
|
13 |
"decoder_layerdrop": 0.0,
|
14 |
"decoder_layers": 12,
|
15 |
"decoder_start_token_id": 2,
|
16 |
-
"do_sample": false,
|
17 |
"dropout": 0.1,
|
18 |
"encoder_attention_heads": 16,
|
19 |
"encoder_ffn_dim": 4096,
|
20 |
"encoder_layerdrop": 0.0,
|
21 |
"encoder_layers": 12,
|
22 |
-
"
|
23 |
"id2label": {
|
24 |
"0": "LABEL_0",
|
25 |
"1": "LABEL_1",
|
26 |
"2": "LABEL_2"
|
27 |
},
|
28 |
"init_std": 0.02,
|
29 |
-
"
|
30 |
"label2id": {
|
31 |
"LABEL_0": 0,
|
32 |
"LABEL_1": 1,
|
33 |
"LABEL_2": 2
|
34 |
},
|
35 |
-
"length_penalty": 1.0,
|
36 |
-
"max_length": 20,
|
37 |
"max_position_embeddings": 1024,
|
38 |
"model_type": "bart",
|
39 |
-
"
|
40 |
"num_hidden_layers": 12,
|
41 |
-
"num_labels": 3,
|
42 |
-
"num_return_sequences": 1,
|
43 |
-
"output_attentions": false,
|
44 |
-
"output_hidden_states": false,
|
45 |
"output_past": false,
|
|
|
46 |
"prefix": " ",
|
47 |
-
"
|
48 |
-
"repetition_penalty": 1.0,
|
49 |
"task_specific_params": {
|
50 |
"summarization": {
|
51 |
"early_stopping": true,
|
@@ -56,10 +53,5 @@
|
|
56 |
"num_beams": 4
|
57 |
}
|
58 |
},
|
59 |
-
"temperature": 1.0,
|
60 |
-
"top_k": 50,
|
61 |
-
"top_p": 1.0,
|
62 |
-
"torchscript": false,
|
63 |
-
"use_bfloat16": false,
|
64 |
"vocab_size": 50265
|
65 |
-
}
|
|
|
1 |
{
|
2 |
+
"_num_labels": 3,
|
3 |
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_final_layer_norm": false,
|
6 |
"architectures": [
|
7 |
"BartModel",
|
8 |
"BartForMaskedLM",
|
9 |
"BartForSequenceClassification"
|
10 |
],
|
11 |
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
"classif_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
|
|
17 |
"decoder_layerdrop": 0.0,
|
18 |
"decoder_layers": 12,
|
19 |
"decoder_start_token_id": 2,
|
|
|
20 |
"dropout": 0.1,
|
21 |
"encoder_attention_heads": 16,
|
22 |
"encoder_ffn_dim": 4096,
|
23 |
"encoder_layerdrop": 0.0,
|
24 |
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 2,
|
26 |
"id2label": {
|
27 |
"0": "LABEL_0",
|
28 |
"1": "LABEL_1",
|
29 |
"2": "LABEL_2"
|
30 |
},
|
31 |
"init_std": 0.02,
|
32 |
+
"is_encoder_decoder": true,
|
33 |
"label2id": {
|
34 |
"LABEL_0": 0,
|
35 |
"LABEL_1": 1,
|
36 |
"LABEL_2": 2
|
37 |
},
|
|
|
|
|
38 |
"max_position_embeddings": 1024,
|
39 |
"model_type": "bart",
|
40 |
+
"normalize_before": false,
|
41 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
|
|
42 |
"output_past": false,
|
43 |
+
"pad_token_id": 1,
|
44 |
"prefix": " ",
|
45 |
+
"scale_embedding": false,
|
|
|
46 |
"task_specific_params": {
|
47 |
"summarization": {
|
48 |
"early_stopping": true,
|
|
|
53 |
"num_beams": 4
|
54 |
}
|
55 |
},
|
|
|
|
|
|
|
|
|
|
|
56 |
"vocab_size": 50265
|
57 |
+
}
|