Hugging Face's logo

satjawat
/
pegasus-x-thai-sum

Summarization
Transformers
Safetensors
Thai
pegasus_x
text2text-generation
Inference Endpoints
Model card Files Community
1
satjawat commited on
Commit
eb2741c
•
1 Parent(s): 78c9799

Initial commit

Browse files
Files changed (7) hide show
  1. config.json +60 -0
  2. generation_config.json +12 -0
  3. model.safetensors +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +20 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +84 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pegasus/trained/model_final_config",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": true,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "PegasusForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "block_size": 512,
12
+ "bos_token_id": 0,
13
+ "classif_dropout": 0.0,
14
+ "classifier_dropout": 0.0,
15
+ "d_model": 768,
16
+ "decoder_attention_heads": 12,
17
+ "decoder_ffn_dim": 3072,
18
+ "decoder_layerdrop": 0.0,
19
+ "decoder_layers": 12,
20
+ "decoder_start_token_id": 0,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 12,
26
+ "eos_token_id": 1,
27
+ "extra_pos_embeddings": 1,
28
+ "force_bos_token_to_be_generated": false,
29
+ "forced_eos_token_id": 1,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 0.8,
44
+ "max_length": 16384,
45
+ "max_position_embeddings": 16384,
46
+ "model_type": "pegasus_x",
47
+ "normalize_before": false,
48
+ "normalize_embedding": true,
49
+ "num_beams": 6,
50
+ "num_global_tokens": 128,
51
+ "num_hidden_layers": 12,
52
+ "pad_token_id": 0,
53
+ "scale_embedding": true,
54
+ "stagger_local_blocks": true,
55
+ "static_position_embeddings": true,
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.36.0",
58
+ "use_cache": true,
59
+ "vocab_size": 96103
60
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "length_penalty": 0.8,
8
+ "max_length": 16384,
9
+ "num_beams": 8,
10
+ "pad_token_id": 0,
11
+ "transformers_version": "4.36.0"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f6ee26b6c40af7a7f915da0ec7c716d02c375aad90e573e31569e2b4d52a925
3
+ size 1190250708
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c4ba4e495ddf31eb2fdba7fc6aef3c233091d25d35bc9d24694ccf48ae114c
3
+ size 904693
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<_>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "8": {
52
+ "content": "<_>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "25004": {
60
+ "content": "<mask>",
61
+ "lstrip": true,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ }
67
+ },
68
+ "additional_special_tokens": [
69
+ "<s>NOTUSED",
70
+ "</s>NOTUSED",
71
+ "<_>"
72
+ ],
73
+ "bos_token": "<s>",
74
+ "clean_up_tokenization_spaces": true,
75
+ "cls_token": "<s>",
76
+ "eos_token": "</s>",
77
+ "mask_token": "<mask>",
78
+ "model_max_length": 1000000000000000019884624838656,
79
+ "pad_token": "<pad>",
80
+ "sep_token": "</s>",
81
+ "sp_model_kwargs": {},
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }