sappho192 commited on
Commit
12c0a8b
1 Parent(s): dcc1dce

Adding ONNX file of this model (#1)

Browse files

- Adding ONNX file of this model (5e3ab68ca01046aab6c25034c0a0541d01711a8b)

onnx/config.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sappho192/jesc-ja-en-translator",
3
+ "architectures": [
4
+ "EncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "openai-community/gpt2",
8
+ "activation_function": "gelu_new",
9
+ "add_cross_attention": true,
10
+ "architectures": [
11
+ "GPT2LMHeadModel"
12
+ ],
13
+ "attn_pdrop": 0.1,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 50256,
17
+ "chunk_size_feed_forward": 0,
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
+ "embd_pdrop": 0.1,
24
+ "encoder_no_repeat_ngram_size": 0,
25
+ "eos_token_id": 50256,
26
+ "exponential_decay_length_penalty": null,
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": false,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-05,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "gpt2",
46
+ "n_ctx": 1024,
47
+ "n_embd": 768,
48
+ "n_head": 12,
49
+ "n_inner": null,
50
+ "n_layer": 12,
51
+ "n_positions": 1024,
52
+ "no_repeat_ngram_size": 0,
53
+ "num_beam_groups": 1,
54
+ "num_beams": 1,
55
+ "num_return_sequences": 1,
56
+ "output_attentions": false,
57
+ "output_hidden_states": false,
58
+ "output_scores": false,
59
+ "pad_token_id": null,
60
+ "prefix": null,
61
+ "problem_type": null,
62
+ "pruned_heads": {},
63
+ "remove_invalid_values": false,
64
+ "reorder_and_upcast_attn": false,
65
+ "repetition_penalty": 1.0,
66
+ "resid_pdrop": 0.1,
67
+ "return_dict": true,
68
+ "return_dict_in_generate": false,
69
+ "scale_attn_by_inverse_layer_idx": false,
70
+ "scale_attn_weights": true,
71
+ "sep_token_id": null,
72
+ "summary_activation": null,
73
+ "summary_first_dropout": 0.1,
74
+ "summary_proj_to_labels": true,
75
+ "summary_type": "cls_index",
76
+ "summary_use_proj": true,
77
+ "suppress_tokens": null,
78
+ "task_specific_params": {
79
+ "text-generation": {
80
+ "do_sample": true,
81
+ "max_length": 50
82
+ }
83
+ },
84
+ "temperature": 1.0,
85
+ "tf_legacy_loss": false,
86
+ "tie_encoder_decoder": false,
87
+ "tie_word_embeddings": true,
88
+ "tokenizer_class": null,
89
+ "top_k": 50,
90
+ "top_p": 1.0,
91
+ "torch_dtype": null,
92
+ "torchscript": false,
93
+ "typical_p": 1.0,
94
+ "use_bfloat16": false,
95
+ "use_cache": true,
96
+ "vocab_size": 50257
97
+ },
98
+ "decoder_start_token_id": 50256,
99
+ "encoder": {
100
+ "_name_or_path": "cl-tohoku/bert-base-japanese-v2",
101
+ "add_cross_attention": false,
102
+ "architectures": [
103
+ "BertForMaskedLM"
104
+ ],
105
+ "attention_probs_dropout_prob": 0.1,
106
+ "bad_words_ids": null,
107
+ "begin_suppress_tokens": null,
108
+ "bos_token_id": null,
109
+ "chunk_size_feed_forward": 0,
110
+ "classifier_dropout": null,
111
+ "cross_attention_hidden_size": null,
112
+ "decoder_start_token_id": null,
113
+ "diversity_penalty": 0.0,
114
+ "do_sample": false,
115
+ "early_stopping": false,
116
+ "encoder_no_repeat_ngram_size": 0,
117
+ "eos_token_id": null,
118
+ "exponential_decay_length_penalty": null,
119
+ "finetuning_task": null,
120
+ "forced_bos_token_id": null,
121
+ "forced_eos_token_id": null,
122
+ "hidden_act": "gelu",
123
+ "hidden_dropout_prob": 0.1,
124
+ "hidden_size": 768,
125
+ "id2label": {
126
+ "0": "LABEL_0",
127
+ "1": "LABEL_1"
128
+ },
129
+ "initializer_range": 0.02,
130
+ "intermediate_size": 3072,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-12,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "max_position_embeddings": 512,
141
+ "min_length": 0,
142
+ "model_type": "bert",
143
+ "no_repeat_ngram_size": 0,
144
+ "num_attention_heads": 12,
145
+ "num_beam_groups": 1,
146
+ "num_beams": 1,
147
+ "num_hidden_layers": 12,
148
+ "num_return_sequences": 1,
149
+ "output_attentions": false,
150
+ "output_hidden_states": false,
151
+ "output_scores": false,
152
+ "pad_token_id": 0,
153
+ "position_embedding_type": "absolute",
154
+ "prefix": null,
155
+ "problem_type": null,
156
+ "pruned_heads": {},
157
+ "remove_invalid_values": false,
158
+ "repetition_penalty": 1.0,
159
+ "return_dict": true,
160
+ "return_dict_in_generate": false,
161
+ "sep_token_id": null,
162
+ "suppress_tokens": null,
163
+ "task_specific_params": null,
164
+ "temperature": 1.0,
165
+ "tf_legacy_loss": false,
166
+ "tie_encoder_decoder": false,
167
+ "tie_word_embeddings": true,
168
+ "tokenizer_class": "BertJapaneseTokenizer",
169
+ "top_k": 50,
170
+ "top_p": 1.0,
171
+ "torch_dtype": null,
172
+ "torchscript": false,
173
+ "type_vocab_size": 2,
174
+ "typical_p": 1.0,
175
+ "use_bfloat16": false,
176
+ "use_cache": true,
177
+ "vocab_size": 32768
178
+ },
179
+ "is_encoder_decoder": true,
180
+ "model_type": "encoder-decoder",
181
+ "pad_token_id": 50256,
182
+ "transformers_version": "4.37.2"
183
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:571cd98eaa237b8d7300f696cdf54a44780dcaa33f22851d5b1095c123f6a15a
3
+ size 767518619
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b43d7160c7a819821f92de40393012f648a48cc2e09281203673b866ee9c342
3
+ size 769413171
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45db16c1fe385ef66ce5d80af9ee5ed20c133b51ca4f71cd4b1805da03eab12b
3
+ size 767515927
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67fecc4c2d07f6a573f917ee4703c97a82ef6552c8e65d3901fb923afcb76bbb
3
+ size 442716948
onnx/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.37.2"
7
+ }