Hugging Face's logo

BME-TMIT
/
foszt2oszt

Text2Text Generation
Transformers
PyTorch
Hungarian
encoder-decoder
Inference Endpoints
Model card Files Community
makrai commited on
Commit
a07d485
•
1 Parent(s): 4ed60b7

add model

Browse files
Files changed (2) hide show
  1. config.json +170 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/permanent/Language/Hungarian/Embed/hubert2hubert-summ/lead-without-title/checkpoint-52500/",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
8
+ "add_cross_attention": true,
9
+ "architectures": null,
10
+ "attention_probs_dropout_prob": 0.1,
11
+ "bad_words_ids": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "classifier_dropout": null,
15
+ "cross_attention_hidden_size": null,
16
+ "decoder_start_token_id": null,
17
+ "diversity_penalty": 0.0,
18
+ "do_sample": false,
19
+ "early_stopping": false,
20
+ "encoder_no_repeat_ngram_size": 0,
21
+ "eos_token_id": null,
22
+ "finetuning_task": null,
23
+ "forced_bos_token_id": null,
24
+ "forced_eos_token_id": null,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1"
32
+ },
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_eps": 1e-12,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "max_position_embeddings": 512,
45
+ "min_length": 0,
46
+ "model_type": "bert",
47
+ "no_repeat_ngram_size": 0,
48
+ "num_attention_heads": 12,
49
+ "num_beam_groups": 1,
50
+ "num_beams": 1,
51
+ "num_hidden_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_scores": false,
56
+ "pad_token_id": 0,
57
+ "position_embedding_type": "absolute",
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "remove_invalid_values": false,
62
+ "repetition_penalty": 1.0,
63
+ "return_dict": true,
64
+ "return_dict_in_generate": false,
65
+ "sep_token_id": null,
66
+ "task_specific_params": null,
67
+ "temperature": 1.0,
68
+ "tie_encoder_decoder": false,
69
+ "tie_word_embeddings": true,
70
+ "tokenizer_class": null,
71
+ "top_k": 50,
72
+ "top_p": 1.0,
73
+ "torch_dtype": null,
74
+ "torchscript": false,
75
+ "transformers_version": "4.15.0",
76
+ "type_vocab_size": 2,
77
+ "use_bfloat16": false,
78
+ "use_cache": true,
79
+ "vocab_size": 32001
80
+ },
81
+ "decoder_start_token_id": 2,
82
+ "early_stopping": true,
83
+ "encoder": {
84
+ "_name_or_path": "SZTAKI-HLT/hubert-base-cc",
85
+ "add_cross_attention": false,
86
+ "architectures": null,
87
+ "attention_probs_dropout_prob": 0.1,
88
+ "bad_words_ids": null,
89
+ "bos_token_id": null,
90
+ "chunk_size_feed_forward": 0,
91
+ "classifier_dropout": null,
92
+ "cross_attention_hidden_size": null,
93
+ "decoder_start_token_id": null,
94
+ "diversity_penalty": 0.0,
95
+ "do_sample": false,
96
+ "early_stopping": false,
97
+ "encoder_no_repeat_ngram_size": 0,
98
+ "eos_token_id": null,
99
+ "finetuning_task": null,
100
+ "forced_bos_token_id": null,
101
+ "forced_eos_token_id": null,
102
+ "gradient_checkpointing": false,
103
+ "hidden_act": "gelu",
104
+ "hidden_dropout_prob": 0.1,
105
+ "hidden_size": 768,
106
+ "id2label": {
107
+ "0": "LABEL_0",
108
+ "1": "LABEL_1"
109
+ },
110
+ "initializer_range": 0.02,
111
+ "intermediate_size": 3072,
112
+ "is_decoder": false,
113
+ "is_encoder_decoder": false,
114
+ "label2id": {
115
+ "LABEL_0": 0,
116
+ "LABEL_1": 1
117
+ },
118
+ "layer_norm_eps": 1e-12,
119
+ "length_penalty": 1.0,
120
+ "max_length": 20,
121
+ "max_position_embeddings": 512,
122
+ "min_length": 0,
123
+ "model_type": "bert",
124
+ "no_repeat_ngram_size": 0,
125
+ "num_attention_heads": 12,
126
+ "num_beam_groups": 1,
127
+ "num_beams": 1,
128
+ "num_hidden_layers": 12,
129
+ "num_return_sequences": 1,
130
+ "output_attentions": false,
131
+ "output_hidden_states": false,
132
+ "output_scores": false,
133
+ "pad_token_id": 0,
134
+ "position_embedding_type": "absolute",
135
+ "prefix": null,
136
+ "problem_type": null,
137
+ "pruned_heads": {},
138
+ "remove_invalid_values": false,
139
+ "repetition_penalty": 1.0,
140
+ "return_dict": true,
141
+ "return_dict_in_generate": false,
142
+ "sep_token_id": null,
143
+ "task_specific_params": null,
144
+ "temperature": 1.0,
145
+ "tie_encoder_decoder": false,
146
+ "tie_word_embeddings": true,
147
+ "tokenizer_class": null,
148
+ "top_k": 50,
149
+ "top_p": 1.0,
150
+ "torch_dtype": null,
151
+ "torchscript": false,
152
+ "transformers_version": "4.15.0",
153
+ "type_vocab_size": 2,
154
+ "use_bfloat16": false,
155
+ "use_cache": true,
156
+ "vocab_size": 32001
157
+ },
158
+ "eos_token_id": 3,
159
+ "is_encoder_decoder": true,
160
+ "length_penalty": 2.0,
161
+ "max_length": 142,
162
+ "min_length": 4,
163
+ "model_type": "encoder-decoder",
164
+ "no_repeat_ngram_size": 3,
165
+ "num_beams": 4,
166
+ "pad_token_id": 0,
167
+ "torch_dtype": "float32",
168
+ "transformers_version": null,
169
+ "vocab_size": 32001
170
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a983d27fe501e0effe7f060c362ed1a4fb2cafb67dca492c2cd8a294037369a
3
+ size 998776914