tehranixyz commited on
Commit
d8160f2
·
verified ·
1 Parent(s): 1a0ff00

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +176 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,176 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_cross_attention": true,
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "cudaizer_fortran_mlm",
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": 1536,
33
+ "id2label": {
34
+ "0": "LABEL_0",
35
+ "1": "LABEL_1"
36
+ },
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 4096,
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": 1026,
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_past": true,
60
+ "output_scores": false,
61
+ "pad_token_id": 1,
62
+ "position_embedding_type": "absolute",
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "pruned_heads": {},
66
+ "remove_invalid_values": false,
67
+ "repetition_penalty": 1.0,
68
+ "return_dict": true,
69
+ "return_dict_in_generate": false,
70
+ "sep_token_id": null,
71
+ "suppress_tokens": null,
72
+ "task_specific_params": null,
73
+ "temperature": 1.0,
74
+ "tf_legacy_loss": false,
75
+ "tie_encoder_decoder": false,
76
+ "tie_word_embeddings": true,
77
+ "tokenizer_class": null,
78
+ "top_k": 50,
79
+ "top_p": 1.0,
80
+ "torch_dtype": "float32",
81
+ "torchscript": false,
82
+ "type_vocab_size": 10,
83
+ "typical_p": 1.0,
84
+ "use_bfloat16": false,
85
+ "use_cache": true,
86
+ "vocab_size": 51418
87
+ },
88
+ "encoder": {
89
+ "_name_or_path": "cudaizer_fortran_mlm",
90
+ "add_cross_attention": false,
91
+ "architectures": [
92
+ "RobertaForMaskedLM"
93
+ ],
94
+ "attention_probs_dropout_prob": 0.1,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": 0,
98
+ "chunk_size_feed_forward": 0,
99
+ "classifier_dropout": null,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "diversity_penalty": 0.0,
103
+ "do_sample": false,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": 2,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "gradient_checkpointing": false,
112
+ "hidden_act": "gelu",
113
+ "hidden_dropout_prob": 0.1,
114
+ "hidden_size": 1536,
115
+ "id2label": {
116
+ "0": "LABEL_0",
117
+ "1": "LABEL_1"
118
+ },
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "max_position_embeddings": 1026,
131
+ "min_length": 0,
132
+ "model_type": "roberta",
133
+ "no_repeat_ngram_size": 0,
134
+ "num_attention_heads": 12,
135
+ "num_beam_groups": 1,
136
+ "num_beams": 1,
137
+ "num_hidden_layers": 12,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_past": true,
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": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": "float32",
163
+ "torchscript": false,
164
+ "type_vocab_size": 10,
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false,
167
+ "use_cache": true,
168
+ "vocab_size": 51418
169
+ },
170
+ "eos_token_id": 2,
171
+ "is_encoder_decoder": true,
172
+ "model_type": "encoder-decoder",
173
+ "pad_token_id": 1,
174
+ "torch_dtype": "float32",
175
+ "transformers_version": "4.40.1"
176
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.40.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff4e286547fd513c8d8e6bce884751faa1f967acc154d5f0135ca5c40b6e3da
3
+ size 3232828176