Hugging Face's logo

Xenova
/
opus-mt-vi-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
4c09a6c
·
1 Parent(s): dd0754f

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-vi-en",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "swish",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "MarianMTModel"
9
+ ],
10
+ "attention_dropout": 0.0,
11
+ "bad_words_ids": [
12
+ [
13
+ 53738
14
+ ]
15
+ ],
16
+ "bos_token_id": 0,
17
+ "classif_dropout": 0.0,
18
+ "classifier_dropout": 0.0,
19
+ "d_model": 512,
20
+ "decoder_attention_heads": 8,
21
+ "decoder_ffn_dim": 2048,
22
+ "decoder_layerdrop": 0.0,
23
+ "decoder_layers": 6,
24
+ "decoder_start_token_id": 53738,
25
+ "decoder_vocab_size": 53739,
26
+ "dropout": 0.1,
27
+ "encoder_attention_heads": 8,
28
+ "encoder_ffn_dim": 2048,
29
+ "encoder_layerdrop": 0.0,
30
+ "encoder_layers": 6,
31
+ "eos_token_id": 0,
32
+ "extra_pos_embeddings": 53739,
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": 53738,
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": 53739
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 53738
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 53738,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 6,
14
+ "pad_token_id": 53738,
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:a99fb73b7a3934f524662745d11070bb1211f79eb1eb5a70aa097e2082fe393a
3
+ size 322551460
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7000434b1823a202bdabb4061912fc7cf24e59ce6b8bfd57751758fdcae2ad1b
3
+ size 322786942
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80862a4a8821363ed2455cc9d248364efd47e83c901acebc92bccde9e07cbe74
3
+ size 82186086
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e9c242c6bfe83143ba529f71ed212d3c3264a94032f75511ed296c920e8e56
3
+ size 81814730
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:192903fd8b7565b384618f1201530717c68916c02795c9b0ffcb811d700100d9
3
+ size 309900951
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:646fe7bcb8f72f13cafeffc4a513d1fb2755e66047e9959b67e49eefadb580b5
3
+ size 78543266
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8ec4bea7eca3e45195cb4c498371af13e2c923fab3f107199fcbdb419c7bea
3
+ size 186873644
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7bd78e8bed6bdc03728f62f1592c4bb52d9e12795496604c1e990e102abdb2
3
+ size 47133597
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
+ "Gather",
8
+ "Transpose",
9
+ "Cast",
10
+ "Pow",
11
+ "Concat",
12
+ "Reshape",
13
+ "Expand",
14
+ "Constant",
15
+ "Mul",
16
+ "Sqrt",
17
+ "ConstantOfShape",
18
+ "Range",
19
+ "Unsqueeze",
20
+ "Where",
21
+ "Sub",
22
+ "ReduceMean",
23
+ "Softmax",
24
+ "Sigmoid",
25
+ "Div",
26
+ "MatMul",
27
+ "Add",
28
+ "Equal",
29
+ "Shape"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "Gather",
36
+ "Transpose",
37
+ "Cast",
38
+ "Pow",
39
+ "Concat",
40
+ "Reshape",
41
+ "Expand",
42
+ "Constant",
43
+ "Mul",
44
+ "Sqrt",
45
+ "ConstantOfShape",
46
+ "Range",
47
+ "Unsqueeze",
48
+ "Where",
49
+ "Sub",
50
+ "ReduceMean",
51
+ "Softmax",
52
+ "Sigmoid",
53
+ "Div",
54
+ "MatMul",
55
+ "Add",
56
+ "Equal",
57
+ "Shape"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "Gather",
64
+ "Transpose",
65
+ "Cast",
66
+ "Pow",
67
+ "Concat",
68
+ "Reshape",
69
+ "Slice",
70
+ "Squeeze",
71
+ "Expand",
72
+ "Constant",
73
+ "Mul",
74
+ "Sqrt",
75
+ "ConstantOfShape",
76
+ "Range",
77
+ "Unsqueeze",
78
+ "Where",
79
+ "Sub",
80
+ "Softmax",
81
+ "ReduceMean",
82
+ "Sigmoid",
83
+ "Div",
84
+ "MatMul",
85
+ "Add",
86
+ "Less",
87
+ "Equal",
88
+ "Shape"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Gather",
95
+ "Transpose",
96
+ "Cast",
97
+ "Pow",
98
+ "Concat",
99
+ "Reshape",
100
+ "Slice",
101
+ "Squeeze",
102
+ "Expand",
103
+ "Constant",
104
+ "Mul",
105
+ "If",
106
+ "Sqrt",
107
+ "ConstantOfShape",
108
+ "Range",
109
+ "Unsqueeze",
110
+ "Where",
111
+ "Sub",
112
+ "Softmax",
113
+ "ReduceMean",
114
+ "Sigmoid",
115
+ "Div",
116
+ "MatMul",
117
+ "Add",
118
+ "Less",
119
+ "Equal",
120
+ "Shape"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (756 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 (809 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": "vie",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "eng",
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