Hugging Face's logo

PuppetLover
/
Title_generator

Transformers
Safetensors
encoder-decoder
text2text-generation
Model card Files
xet
Community
PuppetLover commited on
Commit
66a0e70
·
verified ·
1 Parent(s): 3afc163

Upload model

Browse files
Files changed (3) hide show
  1. config.json +182 -71
  2. generation_config.json +12 -12
  3. model.safetensors +2 -2
config.json CHANGED
@@ -1,71 +1,182 @@
1
- {
2
- "architectures": [
3
- "EncoderDecoderModel"
4
- ],
5
- "decoder": {
6
- "_attn_implementation_autoset": true,
7
- "_name_or_path": "vinai/phobert-base-v2",
8
- "add_cross_attention": true,
9
- "architectures": [
10
- "RobertaForMaskedLM"
11
- ],
12
- "attention_probs_dropout_prob": 0.1,
13
- "classifier_dropout": null,
14
- "hidden_act": "gelu",
15
- "hidden_dropout_prob": 0.1,
16
- "hidden_size": 768,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 3072,
19
- "is_decoder": true,
20
- "layer_norm_eps": 1e-05,
21
- "max_position_embeddings": 258,
22
- "model_type": "roberta",
23
- "num_attention_heads": 12,
24
- "num_hidden_layers": 12,
25
- "position_embedding_type": "absolute",
26
- "tokenizer_class": "PhobertTokenizer",
27
- "torch_dtype": "float32",
28
- "type_vocab_size": 1,
29
- "use_cache": true,
30
- "vocab_size": 64001
31
- },
32
- "decoder_start_token_id": 0,
33
- "early_stopping": null,
34
- "encoder": {
35
- "_attn_implementation_autoset": true,
36
- "_name_or_path": "vinai/phobert-base-v2",
37
- "architectures": [
38
- "RobertaForMaskedLM"
39
- ],
40
- "attention_probs_dropout_prob": 0.1,
41
- "classifier_dropout": null,
42
- "hidden_act": "gelu",
43
- "hidden_dropout_prob": 0.1,
44
- "hidden_size": 768,
45
- "initializer_range": 0.02,
46
- "intermediate_size": 3072,
47
- "layer_norm_eps": 1e-05,
48
- "max_position_embeddings": 258,
49
- "model_type": "roberta",
50
- "num_attention_heads": 12,
51
- "num_hidden_layers": 12,
52
- "position_embedding_type": "absolute",
53
- "tokenizer_class": "PhobertTokenizer",
54
- "torch_dtype": "float32",
55
- "type_vocab_size": 1,
56
- "use_cache": true,
57
- "vocab_size": 64001
58
- },
59
- "eos_token_id": 2,
60
- "is_encoder_decoder": true,
61
- "length_penalty": null,
62
- "max_length": null,
63
- "model_type": "encoder-decoder",
64
- "no_repeat_ngram_size": null,
65
- "num_beams": null,
66
- "pad_token_id": 2,
67
- "tie_encoder_decoder": true,
68
- "torch_dtype": "float32",
69
- "transformers_version": "4.51.3",
70
- "vocab_size": 64001
71
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "PuppetLover/Title_generator",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_attn_implementation_autoset": true,
8
+ "_name_or_path": "vinai/phobert-base-v2",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "RobertaForMaskedLM"
12
+ ],
13
+ "attention_probs_dropout_prob": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": null,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 2,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "hidden_act": "gelu",
31
+ "hidden_dropout_prob": 0.1,
32
+ "hidden_size": 768,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 3072,
39
+ "is_decoder": true,
40
+ "is_encoder_decoder": false,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "length_penalty": 1.0,
47
+ "max_length": 20,
48
+ "max_position_embeddings": 258,
49
+ "min_length": 0,
50
+ "model_type": "roberta",
51
+ "no_repeat_ngram_size": 0,
52
+ "num_attention_heads": 12,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_hidden_layers": 12,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "position_embedding_type": "absolute",
62
+ "prefix": null,
63
+ "problem_type": null,
64
+ "pruned_heads": {},
65
+ "remove_invalid_values": false,
66
+ "repetition_penalty": 1.0,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": "PhobertTokenizer",
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": "float32",
80
+ "torchscript": false,
81
+ "type_vocab_size": 1,
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "use_cache": true,
85
+ "vocab_size": 64281
86
+ },
87
+ "decoder_start_token_id": 0,
88
+ "early_stopping": null,
89
+ "encoder": {
90
+ "_attn_implementation_autoset": true,
91
+ "_name_or_path": "vinai/phobert-base-v2",
92
+ "add_cross_attention": false,
93
+ "architectures": [
94
+ "RobertaForMaskedLM"
95
+ ],
96
+ "attention_probs_dropout_prob": 0.1,
97
+ "bad_words_ids": null,
98
+ "begin_suppress_tokens": null,
99
+ "bos_token_id": 0,
100
+ "chunk_size_feed_forward": 0,
101
+ "classifier_dropout": null,
102
+ "cross_attention_hidden_size": null,
103
+ "decoder_start_token_id": null,
104
+ "diversity_penalty": 0.0,
105
+ "do_sample": false,
106
+ "early_stopping": false,
107
+ "encoder_no_repeat_ngram_size": 0,
108
+ "eos_token_id": 2,
109
+ "exponential_decay_length_penalty": null,
110
+ "finetuning_task": null,
111
+ "forced_bos_token_id": null,
112
+ "forced_eos_token_id": null,
113
+ "hidden_act": "gelu",
114
+ "hidden_dropout_prob": 0.1,
115
+ "hidden_size": 768,
116
+ "id2label": {
117
+ "0": "LABEL_0",
118
+ "1": "LABEL_1"
119
+ },
120
+ "initializer_range": 0.02,
121
+ "intermediate_size": 3072,
122
+ "is_decoder": false,
123
+ "is_encoder_decoder": false,
124
+ "label2id": {
125
+ "LABEL_0": 0,
126
+ "LABEL_1": 1
127
+ },
128
+ "layer_norm_eps": 1e-05,
129
+ "length_penalty": 1.0,
130
+ "max_length": 20,
131
+ "max_position_embeddings": 258,
132
+ "min_length": 0,
133
+ "model_type": "roberta",
134
+ "no_repeat_ngram_size": 0,
135
+ "num_attention_heads": 12,
136
+ "num_beam_groups": 1,
137
+ "num_beams": 1,
138
+ "num_hidden_layers": 12,
139
+ "num_return_sequences": 1,
140
+ "output_attentions": false,
141
+ "output_hidden_states": false,
142
+ "output_scores": false,
143
+ "pad_token_id": 1,
144
+ "position_embedding_type": "absolute",
145
+ "prefix": null,
146
+ "problem_type": null,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": "PhobertTokenizer",
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": "float32",
163
+ "torchscript": false,
164
+ "type_vocab_size": 1,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 64281
169
+ },
170
+ "eos_token_id": 2,
171
+ "is_encoder_decoder": true,
172
+ "length_penalty": null,
173
+ "max_length": null,
174
+ "model_type": "encoder-decoder",
175
+ "no_repeat_ngram_size": null,
176
+ "num_beams": null,
177
+ "pad_token_id": 2,
178
+ "tie_encoder_decoder": true,
179
+ "torch_dtype": "float32",
180
+ "transformers_version": "4.49.0",
181
+ "vocab_size": 64001
182
+ }
generation_config.json CHANGED
@@ -1,12 +1,12 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "early_stopping": true,
5
- "eos_token_id": 2,
6
- "length_penalty": 2.0,
7
- "max_length": 64,
8
- "no_repeat_ngram_size": 3,
9
- "num_beams": 4,
10
- "pad_token_id": 1,
11
- "transformers_version": "4.51.3"
12
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "early_stopping": true,
5
+ "eos_token_id": 2,
6
+ "length_penalty": 2.0,
7
+ "max_length": 64,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.49.0"
12
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e22bceb8efde6c16edab581d9b1011a4732e34e442006f2eb6fbb7899ee60a77
3
- size 656127340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f549ff0428bcf63421b404fa5bd46bd9d860b2cbd55c834a6062b9def91d6689
3
+ size 656988620