Update config.json
Browse files- config.json +4 -15
config.json
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
"_num_labels": 3,
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
|
|
5 |
"architectures": [
|
6 |
"BartForConditionalGeneration"
|
7 |
],
|
@@ -14,7 +15,6 @@
|
|
14 |
"decoder_layerdrop": 0.0,
|
15 |
"decoder_layers": 12,
|
16 |
"decoder_start_token_id": 2,
|
17 |
-
"do_sample": false,
|
18 |
"dropout": 0.1,
|
19 |
"early_stopping": true,
|
20 |
"encoder_attention_heads": 16,
|
@@ -25,36 +25,30 @@
|
|
25 |
"eos_token_ids": [
|
26 |
2
|
27 |
],
|
28 |
-
"finetuning_task": null,
|
29 |
"id2label": {
|
30 |
"0": "LABEL_0",
|
31 |
"1": "LABEL_1",
|
32 |
"2": "LABEL_2"
|
33 |
},
|
34 |
"init_std": 0.02,
|
35 |
-
"is_decoder": false,
|
36 |
"is_encoder_decoder": true,
|
37 |
"label2id": {
|
38 |
"LABEL_0": 0,
|
39 |
"LABEL_1": 1,
|
40 |
"LABEL_2": 2
|
41 |
},
|
42 |
-
"length_penalty": 1.0,
|
43 |
"max_length": 62,
|
44 |
"max_position_embeddings": 1024,
|
45 |
"min_length": 11,
|
46 |
"model_type": "bart",
|
47 |
"no_repeat_ngram_size": 3,
|
|
|
48 |
"num_beams": 6,
|
49 |
"num_hidden_layers": 12,
|
50 |
-
"num_return_sequences": 1,
|
51 |
-
"output_attentions": false,
|
52 |
-
"output_hidden_states": false,
|
53 |
"output_past": true,
|
54 |
"pad_token_id": 1,
|
55 |
"prefix": " ",
|
56 |
-
"
|
57 |
-
"repetition_penalty": 1.0,
|
58 |
"task_specific_params": {
|
59 |
"summarization": {
|
60 |
"early_stopping": true,
|
@@ -65,10 +59,5 @@
|
|
65 |
"num_beams": 4
|
66 |
}
|
67 |
},
|
68 |
-
"temperature": 1.0,
|
69 |
-
"top_k": 50,
|
70 |
-
"top_p": 1.0,
|
71 |
-
"torchscript": false,
|
72 |
-
"use_bfloat16": false,
|
73 |
"vocab_size": 50264
|
74 |
-
}
|
|
|
2 |
"_num_labels": 3,
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
+
"add_final_layer_norm": false,
|
6 |
"architectures": [
|
7 |
"BartForConditionalGeneration"
|
8 |
],
|
|
|
15 |
"decoder_layerdrop": 0.0,
|
16 |
"decoder_layers": 12,
|
17 |
"decoder_start_token_id": 2,
|
|
|
18 |
"dropout": 0.1,
|
19 |
"early_stopping": true,
|
20 |
"encoder_attention_heads": 16,
|
|
|
25 |
"eos_token_ids": [
|
26 |
2
|
27 |
],
|
|
|
28 |
"id2label": {
|
29 |
"0": "LABEL_0",
|
30 |
"1": "LABEL_1",
|
31 |
"2": "LABEL_2"
|
32 |
},
|
33 |
"init_std": 0.02,
|
|
|
34 |
"is_encoder_decoder": true,
|
35 |
"label2id": {
|
36 |
"LABEL_0": 0,
|
37 |
"LABEL_1": 1,
|
38 |
"LABEL_2": 2
|
39 |
},
|
|
|
40 |
"max_length": 62,
|
41 |
"max_position_embeddings": 1024,
|
42 |
"min_length": 11,
|
43 |
"model_type": "bart",
|
44 |
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
"num_beams": 6,
|
47 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
48 |
"output_past": true,
|
49 |
"pad_token_id": 1,
|
50 |
"prefix": " ",
|
51 |
+
"scale_embedding": false,
|
|
|
52 |
"task_specific_params": {
|
53 |
"summarization": {
|
54 |
"early_stopping": true,
|
|
|
59 |
"num_beams": 4
|
60 |
}
|
61 |
},
|
|
|
|
|
|
|
|
|
|
|
62 |
"vocab_size": 50264
|
63 |
+
}
|