harsharajkumar273 commited on
Commit
1fd527b
·
verified ·
1 Parent(s): d855bca

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/prophetnet-large-uncased-cnndm",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_cross_attention": true,
6
+ "architectures": [
7
+ "ProphetNetForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 102,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0.0,
13
+ "decoder_max_position_embeddings": 514,
14
+ "decoder_start_token_id": 102,
15
+ "disable_ngram_loss": false,
16
+ "dropout": 0.1,
17
+ "encoder_ffn_dim": 4096,
18
+ "encoder_layerdrop": 0.0,
19
+ "encoder_max_position_embeddings": 513,
20
+ "eos_token_id": 102,
21
+ "eps": 0.0,
22
+ "hidden_size": 1024,
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": 512,
36
+ "model_type": "prophetnet",
37
+ "ngram": 2,
38
+ "num_buckets": 32,
39
+ "num_decoder_attention_heads": 16,
40
+ "num_decoder_layers": 12,
41
+ "num_encoder_attention_heads": 16,
42
+ "num_encoder_layers": 12,
43
+ "output_past": false,
44
+ "pad_token_id": 0,
45
+ "prefix": " ",
46
+ "relative_max_distance": 128,
47
+ "task_specific_params": {
48
+ "summarization": {
49
+ "early_stopping": true,
50
+ "length_penalty": 1.2,
51
+ "no_repeat_ngram_size": 3,
52
+ "num_beams": 5
53
+ }
54
+ },
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.49.0",
57
+ "use_cache": false,
58
+ "vocab_size": 30522
59
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 102,
3
+ "decoder_start_token_id": 102,
4
+ "eos_token_id": 102,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.49.0"
7
+ }
prophetnet.tokenizer ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[SEP]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[MASK]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "clean_up_tokenization_spaces": true,
37
+ "cls_token": "[SEP]",
38
+ "do_basic_tokenize": true,
39
+ "do_lower_case": true,
40
+ "extra_special_tokens": {},
41
+ "full_tokenizer_file": null,
42
+ "mask_token": "[MASK]",
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "never_split": null,
45
+ "pad_token": "[PAD]",
46
+ "sep_token": "[SEP]",
47
+ "strip_accents": null,
48
+ "tokenize_chinese_chars": true,
49
+ "tokenizer_class": "ProphetNetTokenizer",
50
+ "unk_token": "[UNK]",
51
+ "x_sep_token": "[X_SEP]",
52
+ "xprophetnet_tokenizer": false
53
+ }