Hugging Face's logo

KhoaUIT
/
Phobert2Phobert

Text2Text Generation
Transformers
Safetensors
encoder-decoder
Inference Endpoints
Model card Files Community
KhoaUIT commited on
Commit
294990d
·
verified ·
1 Parent(s): 4a96953

Update config.json

Browse files
Files changed (1) hide show
  1. config.json +181 -181
config.json CHANGED
@@ -1,181 +1,181 @@
1
- {
2
- "_name_or_path": "weight_phobert2phobert/checkpoint-32950",
3
- "architectures": [
4
- "EncoderDecoderModel"
5
- ],
6
- "decoder": {
7
- "_name_or_path": "vinai/phobert-base",
8
- "add_cross_attention": true,
9
- "architectures": [
10
- "RobertaForMaskedLM"
11
- ],
12
- "attention_probs_dropout_prob": 0.1,
13
- "bad_words_ids": null,
14
- "begin_suppress_tokens": null,
15
- "bos_token_id": 0,
16
- "chunk_size_feed_forward": 0,
17
- "classifier_dropout": null,
18
- "cross_attention_hidden_size": null,
19
- "decoder_start_token_id": null,
20
- "diversity_penalty": 0.0,
21
- "do_sample": false,
22
- "early_stopping": false,
23
- "encoder_no_repeat_ngram_size": 0,
24
- "eos_token_id": 2,
25
- "exponential_decay_length_penalty": null,
26
- "finetuning_task": null,
27
- "forced_bos_token_id": null,
28
- "forced_eos_token_id": null,
29
- "gradient_checkpointing": false,
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": null,
80
- "torchscript": false,
81
- "type_vocab_size": 1,
82
- "typical_p": 1.0,
83
- "use_bfloat16": false,
84
- "use_cache": true,
85
- "vocab_size": 64001
86
- },
87
- "decoder_start_token_id": 0,
88
- "early_stopping": null,
89
- "encoder": {
90
- "_name_or_path": "vinai/phobert-base",
91
- "add_cross_attention": false,
92
- "architectures": [
93
- "RobertaForMaskedLM"
94
- ],
95
- "attention_probs_dropout_prob": 0.1,
96
- "bad_words_ids": null,
97
- "begin_suppress_tokens": null,
98
- "bos_token_id": 0,
99
- "chunk_size_feed_forward": 0,
100
- "classifier_dropout": null,
101
- "cross_attention_hidden_size": null,
102
- "decoder_start_token_id": null,
103
- "diversity_penalty": 0.0,
104
- "do_sample": false,
105
- "early_stopping": false,
106
- "encoder_no_repeat_ngram_size": 0,
107
- "eos_token_id": 2,
108
- "exponential_decay_length_penalty": null,
109
- "finetuning_task": null,
110
- "forced_bos_token_id": null,
111
- "forced_eos_token_id": null,
112
- "gradient_checkpointing": false,
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": null,
163
- "torchscript": false,
164
- "type_vocab_size": 1,
165
- "typical_p": 1.0,
166
- "use_bfloat16": false,
167
- "use_cache": true,
168
- "vocab_size": 64001
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": 1,
178
- "torch_dtype": "float32",
179
- "transformers_version": "4.45.2",
180
- "vocab_size": 64001
181
- }
 
1
+ {
2
+ "_name_or_path": "weight_phobert2phobert/checkpoint-32950",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "vinai/phobert-base",
8
+ "add_cross_attention": true,
9
+ "architectures": [
10
+ "RobertaForMaskedLM"
11
+ ],
12
+ "attention_probs_dropout_prob": 0.1,
13
+ "bad_words_ids": null,
14
+ "begin_suppress_tokens": null,
15
+ "bos_token_id": 0,
16
+ "chunk_size_feed_forward": 0,
17
+ "classifier_dropout": null,
18
+ "cross_attention_hidden_size": null,
19
+ "decoder_start_token_id": null,
20
+ "diversity_penalty": 0.0,
21
+ "do_sample": false,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 2,
25
+ "exponential_decay_length_penalty": null,
26
+ "finetuning_task": null,
27
+ "forced_bos_token_id": null,
28
+ "forced_eos_token_id": null,
29
+ "gradient_checkpointing": false,
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": null,
80
+ "torchscript": false,
81
+ "type_vocab_size": 1,
82
+ "typical_p": 1.0,
83
+ "use_bfloat16": false,
84
+ "use_cache": true,
85
+ "vocab_size": 64001
86
+ },
87
+ "decoder_start_token_id": 0,
88
+ "early_stopping": false,
89
+ "encoder": {
90
+ "_name_or_path": "vinai/phobert-base",
91
+ "add_cross_attention": false,
92
+ "architectures": [
93
+ "RobertaForMaskedLM"
94
+ ],
95
+ "attention_probs_dropout_prob": 0.1,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": 0,
99
+ "chunk_size_feed_forward": 0,
100
+ "classifier_dropout": null,
101
+ "cross_attention_hidden_size": null,
102
+ "decoder_start_token_id": null,
103
+ "diversity_penalty": 0.0,
104
+ "do_sample": false,
105
+ "early_stopping": false,
106
+ "encoder_no_repeat_ngram_size": 0,
107
+ "eos_token_id": 2,
108
+ "exponential_decay_length_penalty": null,
109
+ "finetuning_task": null,
110
+ "forced_bos_token_id": null,
111
+ "forced_eos_token_id": null,
112
+ "gradient_checkpointing": false,
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": null,
163
+ "torchscript": false,
164
+ "type_vocab_size": 1,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 64001
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": 1,
178
+ "torch_dtype": "float32",
179
+ "transformers_version": "4.45.2",
180
+ "vocab_size": 64001
181
+ }