Hugging Face's logo

Cohee
/
bart-large-cnn-samsum-ChatGPT-onnx

Summarization
Transformers
ONNX
bart
text2text-generation
Generated from Trainer
Model card Files Community
Cohee commited on
Commit
f75646f
·
1 Parent(s): 2bfb85c

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +69 -0
  2. generation_config.json +16 -0
  3. merges.txt +0 -0
  4. quantize_config.json +125 -0
  5. special_tokens_map.json +15 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +68 -0
  8. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qiliang/bart-large-cnn-samsum-ChatGPT_v3",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "gelu",
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,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
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
+ "force_bos_token_to_be_generated": true,
28
+ "forced_bos_token_id": 0,
29
+ "forced_eos_token_id": 2,
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": 2.0,
44
+ "max_length": 142,
45
+ "max_position_embeddings": 1024,
46
+ "min_length": 56,
47
+ "model_type": "bart",
48
+ "no_repeat_ngram_size": 3,
49
+ "normalize_before": false,
50
+ "num_beams": 4,
51
+ "num_hidden_layers": 12,
52
+ "output_past": true,
53
+ "pad_token_id": 1,
54
+ "prefix": " ",
55
+ "scale_embedding": false,
56
+ "task_specific_params": {
57
+ "summarization": {
58
+ "early_stopping": true,
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "no_repeat_ngram_size": 3,
63
+ "num_beams": 4
64
+ }
65
+ },
66
+ "transformers_version": "4.34.0.dev0",
67
+ "use_cache": true,
68
+ "vocab_size": 50264
69
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_bos_token_id": 0,
8
+ "forced_eos_token_id": 2,
9
+ "length_penalty": 2.0,
10
+ "max_length": 142,
11
+ "min_length": 56,
12
+ "no_repeat_ngram_size": 3,
13
+ "num_beams": 4,
14
+ "pad_token_id": 1,
15
+ "transformers_version": "4.34.0.dev0"
16
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "Softmax",
8
+ "Where",
9
+ "Shape",
10
+ "Transpose",
11
+ "Equal",
12
+ "ReduceMean",
13
+ "Sqrt",
14
+ "Sub",
15
+ "Unsqueeze",
16
+ "Constant",
17
+ "Erf",
18
+ "ConstantOfShape",
19
+ "Pow",
20
+ "Concat",
21
+ "Expand",
22
+ "Cast",
23
+ "Range",
24
+ "Reshape",
25
+ "Add",
26
+ "Div",
27
+ "Gather",
28
+ "MatMul",
29
+ "Mul"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_model": {
34
+ "op_types": [
35
+ "Softmax",
36
+ "Where",
37
+ "Shape",
38
+ "Transpose",
39
+ "Equal",
40
+ "ReduceMean",
41
+ "Sqrt",
42
+ "Sub",
43
+ "Unsqueeze",
44
+ "Constant",
45
+ "Less",
46
+ "Erf",
47
+ "ConstantOfShape",
48
+ "Pow",
49
+ "Concat",
50
+ "Expand",
51
+ "Cast",
52
+ "Squeeze",
53
+ "Range",
54
+ "Reshape",
55
+ "Slice",
56
+ "Add",
57
+ "Div",
58
+ "Gather",
59
+ "MatMul",
60
+ "Mul"
61
+ ],
62
+ "weight_type": "QInt8"
63
+ },
64
+ "encoder_model": {
65
+ "op_types": [
66
+ "Softmax",
67
+ "Where",
68
+ "Shape",
69
+ "Transpose",
70
+ "Equal",
71
+ "ReduceMean",
72
+ "Sqrt",
73
+ "Sub",
74
+ "Unsqueeze",
75
+ "Constant",
76
+ "Erf",
77
+ "ConstantOfShape",
78
+ "Pow",
79
+ "Concat",
80
+ "Expand",
81
+ "Cast",
82
+ "Range",
83
+ "Reshape",
84
+ "Add",
85
+ "Div",
86
+ "Gather",
87
+ "MatMul",
88
+ "Mul"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Softmax",
95
+ "Where",
96
+ "Shape",
97
+ "Transpose",
98
+ "Equal",
99
+ "ReduceMean",
100
+ "If",
101
+ "Sqrt",
102
+ "Sub",
103
+ "Unsqueeze",
104
+ "Constant",
105
+ "Less",
106
+ "Erf",
107
+ "ConstantOfShape",
108
+ "Pow",
109
+ "Concat",
110
+ "Expand",
111
+ "Cast",
112
+ "Squeeze",
113
+ "Range",
114
+ "Reshape",
115
+ "Slice",
116
+ "Add",
117
+ "Div",
118
+ "Gather",
119
+ "MatMul",
120
+ "Mul"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_length": 128,
38
+ "model_max_length": 1024,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "stride": 0,
56
+ "tokenizer_class": "BartTokenizer",
57
+ "trim_offsets": true,
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": {
61
+ "__type": "AddedToken",
62
+ "content": "<unk>",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false
67
+ }
68
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff