Hugging Face's logo

Xenova
/
opus-mt-ja-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files
xet
 Community
1
Xenova HF Staff commited on
Commit
7bbb3f5
·
1 Parent(s): 213476b

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. config.json +60 -0
  2. generation_config.json +16 -0
  3. onnx/decoder_model.onnx +3 -0
  4. onnx/decoder_model_merged.onnx +3 -0
  5. onnx/decoder_model_merged_quantized.onnx +3 -0
  6. onnx/decoder_model_quantized.onnx +3 -0
  7. onnx/decoder_with_past_model.onnx +3 -0
  8. onnx/decoder_with_past_model_quantized.onnx +3 -0
  9. onnx/encoder_model.onnx +3 -0
  10. onnx/encoder_model_quantized.onnx +3 -0
  11. quantize_config.json +125 -0
  12. source.spm +0 -0
  13. special_tokens_map.json +5 -0
  14. target.spm +0 -0
  15. tokenizer.json +0 -0
  16. tokenizer_config.json +12 -0
  17. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Helsinki-NLP/opus-mt-ja-en",
3
+ "_num_labels": 3,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "swish",
6
+ "add_bias_logits": false,
7
+ "add_final_layer_norm": false,
8
+ "architectures": [
9
+ "MarianMTModel"
10
+ ],
11
+ "attention_dropout": 0.0,
12
+ "bad_words_ids": [
13
+ [
14
+ 60715
15
+ ]
16
+ ],
17
+ "bos_token_id": 0,
18
+ "classif_dropout": 0.0,
19
+ "classifier_dropout": 0.0,
20
+ "d_model": 512,
21
+ "decoder_attention_heads": 8,
22
+ "decoder_ffn_dim": 2048,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 6,
25
+ "decoder_start_token_id": 60715,
26
+ "decoder_vocab_size": 60716,
27
+ "dropout": 0.1,
28
+ "encoder_attention_heads": 8,
29
+ "encoder_ffn_dim": 2048,
30
+ "encoder_layerdrop": 0.0,
31
+ "encoder_layers": 6,
32
+ "eos_token_id": 0,
33
+ "forced_eos_token_id": 0,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "max_length": 512,
47
+ "max_position_embeddings": 512,
48
+ "model_type": "marian",
49
+ "normalize_before": false,
50
+ "normalize_embedding": false,
51
+ "num_beams": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 60715,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "transformers_version": "4.32.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 60716
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 60715
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 60715,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 60715,
15
+ "transformers_version": "4.32.0.dev0"
16
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52e9b0f0a8bc163976e98be426539ade13091c7a039a6bf20c45e8f797bd781
3
+ size 351157160
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40ab48786dfbee02ca95bb84f9bf77eec378642550f115dc95ac0b9f9c0dc24
3
+ size 351392642
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272ca60e1c3f36faed2052b20796f9e6fa3e2348a80320e82826a5a8c663f95d
3
+ size 89393328
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19cdb07e1ef87404c6f4afd1d7b134a78813403d128cd6da2314782c7c203418
3
+ size 89021972
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecabb9dc89ad4f6b3cc83790066ee2eba1750ddfa4369d2d63f4380aa1be1d61
3
+ size 338506651
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3846fc6322384ca11e29f629d71b4a2cef79cfd97c5aa42967c81a9e2772a406
3
+ size 85750508
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa28e0b0be8af4ea7d32af72ee8d54ba2cb8ac3ac46ab665e46c8d997d9f980
3
+ size 201162540
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:345262b16bcdda1468b0f3380c112b7ce79f731176b4b1d21f6edd5b2ae0d25c
3
+ size 50705822
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "encoder_model": {
6
+ "op_types": [
7
+ "Where",
8
+ "ReduceMean",
9
+ "Expand",
10
+ "Cast",
11
+ "Equal",
12
+ "Range",
13
+ "Sub",
14
+ "Shape",
15
+ "Sqrt",
16
+ "Constant",
17
+ "Reshape",
18
+ "Pow",
19
+ "Softmax",
20
+ "Transpose",
21
+ "ConstantOfShape",
22
+ "Unsqueeze",
23
+ "Gather",
24
+ "MatMul",
25
+ "Add",
26
+ "Div",
27
+ "Mul",
28
+ "Sigmoid",
29
+ "Concat"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "Where",
36
+ "ReduceMean",
37
+ "Expand",
38
+ "Cast",
39
+ "Equal",
40
+ "Range",
41
+ "Sub",
42
+ "Shape",
43
+ "Sqrt",
44
+ "Constant",
45
+ "Reshape",
46
+ "Pow",
47
+ "Softmax",
48
+ "Transpose",
49
+ "ConstantOfShape",
50
+ "Unsqueeze",
51
+ "Gather",
52
+ "MatMul",
53
+ "Add",
54
+ "Div",
55
+ "Mul",
56
+ "Sigmoid",
57
+ "Concat"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "Where",
64
+ "ReduceMean",
65
+ "Expand",
66
+ "Cast",
67
+ "Equal",
68
+ "Range",
69
+ "Sub",
70
+ "Shape",
71
+ "Sqrt",
72
+ "Constant",
73
+ "Reshape",
74
+ "Pow",
75
+ "Softmax",
76
+ "Less",
77
+ "ConstantOfShape",
78
+ "Unsqueeze",
79
+ "Gather",
80
+ "Transpose",
81
+ "MatMul",
82
+ "Add",
83
+ "Squeeze",
84
+ "Div",
85
+ "Mul",
86
+ "Sigmoid",
87
+ "Slice",
88
+ "Concat"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Where",
95
+ "ReduceMean",
96
+ "If",
97
+ "Expand",
98
+ "Cast",
99
+ "Equal",
100
+ "Range",
101
+ "Sub",
102
+ "Shape",
103
+ "Sqrt",
104
+ "Constant",
105
+ "Reshape",
106
+ "Pow",
107
+ "Softmax",
108
+ "Less",
109
+ "ConstantOfShape",
110
+ "Unsqueeze",
111
+ "Gather",
112
+ "Transpose",
113
+ "MatMul",
114
+ "Add",
115
+ "Squeeze",
116
+ "Div",
117
+ "Mul",
118
+ "Sigmoid",
119
+ "Slice",
120
+ "Concat"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (782 kB). View file
 
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
target.spm ADDED
Binary file (802 kB). View file
 
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "eos_token": "</s>",
4
+ "model_max_length": 512,
5
+ "pad_token": "<pad>",
6
+ "separate_vocabs": false,
7
+ "source_lang": "ja",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "en",
10
+ "tokenizer_class": "MarianTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff