nicoladecao
commited on
Commit
•
ee87331
1
Parent(s):
f168350
cleaning update
Browse files- config.json +13 -22
- special_tokens_map.json +51 -0
- tokenizer_config.json +64 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,15 +1,11 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/genre-kilt",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
-
"add_bias_logits": false,
|
6 |
-
"add_final_layer_norm": false,
|
7 |
"architectures": [
|
8 |
"BartForConditionalGeneration"
|
9 |
],
|
10 |
"attention_dropout": 0.0,
|
11 |
"bos_token_id": 0,
|
12 |
-
"classif_dropout": 0.0,
|
13 |
"classifier_dropout": 0.0,
|
14 |
"d_model": 1024,
|
15 |
"decoder_attention_heads": 16,
|
@@ -18,36 +14,31 @@
|
|
18 |
"decoder_layers": 12,
|
19 |
"decoder_start_token_id": 2,
|
20 |
"dropout": 0.1,
|
21 |
-
"early_stopping": true,
|
22 |
"encoder_attention_heads": 16,
|
23 |
"encoder_ffn_dim": 4096,
|
24 |
"encoder_layerdrop": 0.0,
|
25 |
"encoder_layers": 12,
|
26 |
"eos_token_id": 2,
|
27 |
-
"eos_token_ids": [
|
28 |
-
2
|
29 |
-
],
|
30 |
"forced_eos_token_id": 2,
|
31 |
-
"
|
|
|
|
|
|
|
|
|
32 |
"init_std": 0.02,
|
33 |
"is_encoder_decoder": true,
|
34 |
-
"
|
|
|
|
|
|
|
|
|
35 |
"max_position_embeddings": 1024,
|
36 |
-
"min_length": 0,
|
37 |
"model_type": "bart",
|
38 |
-
"normalize_before": false,
|
39 |
-
"normalize_embedding": false,
|
40 |
-
"num_beams": 6,
|
41 |
"num_hidden_layers": 12,
|
42 |
-
"output_past": true,
|
43 |
"pad_token_id": 1,
|
44 |
-
"replacing_rate": 0,
|
45 |
"scale_embedding": false,
|
46 |
-
"
|
47 |
-
"
|
48 |
-
"student_encoder_layers": null,
|
49 |
-
"task_specific_params": {},
|
50 |
-
"transformers_version": "4.19.2",
|
51 |
"use_cache": true,
|
52 |
"vocab_size": 50264
|
53 |
-
}
|
|
|
1 |
{
|
|
|
2 |
"activation_dropout": 0.0,
|
3 |
"activation_function": "gelu",
|
|
|
|
|
4 |
"architectures": [
|
5 |
"BartForConditionalGeneration"
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"bos_token_id": 0,
|
|
|
9 |
"classifier_dropout": 0.0,
|
10 |
"d_model": 1024,
|
11 |
"decoder_attention_heads": 16,
|
|
|
14 |
"decoder_layers": 12,
|
15 |
"decoder_start_token_id": 2,
|
16 |
"dropout": 0.1,
|
|
|
17 |
"encoder_attention_heads": 16,
|
18 |
"encoder_ffn_dim": 4096,
|
19 |
"encoder_layerdrop": 0.0,
|
20 |
"encoder_layers": 12,
|
21 |
"eos_token_id": 2,
|
|
|
|
|
|
|
22 |
"forced_eos_token_id": 2,
|
23 |
+
"id2label": {
|
24 |
+
"0": "LABEL_0",
|
25 |
+
"1": "LABEL_1",
|
26 |
+
"2": "LABEL_2"
|
27 |
+
},
|
28 |
"init_std": 0.02,
|
29 |
"is_encoder_decoder": true,
|
30 |
+
"label2id": {
|
31 |
+
"LABEL_0": 0,
|
32 |
+
"LABEL_1": 1,
|
33 |
+
"LABEL_2": 2
|
34 |
+
},
|
35 |
"max_position_embeddings": 1024,
|
|
|
36 |
"model_type": "bart",
|
|
|
|
|
|
|
37 |
"num_hidden_layers": 12,
|
|
|
38 |
"pad_token_id": 1,
|
|
|
39 |
"scale_embedding": false,
|
40 |
+
"torch_dtype": "float32",
|
41 |
+
"transformers_version": "4.20.0.dev0",
|
|
|
|
|
|
|
42 |
"use_cache": true,
|
43 |
"vocab_size": 50264
|
44 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1 +1,64 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"errors": "replace",
|
28 |
+
"mask_token": {
|
29 |
+
"__type": "AddedToken",
|
30 |
+
"content": "<mask>",
|
31 |
+
"lstrip": true,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"model_max_length": 1024,
|
37 |
+
"name_or_path": "facebook/bart-large",
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"special_tokens_map_file": null,
|
55 |
+
"tokenizer_class": "BartTokenizer",
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|