Hugging Face's logo

Xenova
/
opus-mt-en-vi

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
dc32528
•
1 Parent(s): 5fa699c

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-en-vi",
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
+ 53684
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": 53684,
25
+ "decoder_vocab_size": 53685,
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": 53685,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 53684,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "transformers_version": "4.33.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 53685
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 53684
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 53684,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 4,
13
+ "pad_token_id": 53684,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.33.0.dev0"
16
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0d893453f8a43d23b576dd6bf3fa1115f1518e3b91d9c40c14dbccb43b7343
3
+ size 322330060
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39f01ded3e54e0bd052238352ffd14242b6a59a843fa1a6c51413ea4f232c3f1
3
+ size 322565542
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1db1532aa7e2ac44e4fc4b5b7a239133c13589aff7ae5af2ebe9ef1df812a123
3
+ size 82130305
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e20ba038bf624f634480c1ad20e466d8b2c83d976ff97040df0af794004632e
3
+ size 81758949
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:283f351d005aba8e3922fed2d646f898dadbed4809602d62469f9ed4e6b62eba
3
+ size 309679551
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6bcc438c2493a8e6aaa818acf203ddd2884785fcbc9ab711fcdba4d29c4aa25
3
+ size 78487485
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be90b557001b7eb13b5056872a079d19f1d459397a0fc1a23809751a9dca91bf
3
+ size 186763052
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcd7a32be3fdd21cbcf5d354520d626f1768fd6e205ca62a6a11a4641d31f36
3
+ size 47105950
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Sqrt",
8
+ "Equal",
9
+ "Cast",
10
+ "Mul",
11
+ "Slice",
12
+ "Gather",
13
+ "Constant",
14
+ "ReduceMean",
15
+ "Div",
16
+ "Squeeze",
17
+ "MatMul",
18
+ "ConstantOfShape",
19
+ "Reshape",
20
+ "Pow",
21
+ "Transpose",
22
+ "Range",
23
+ "Sub",
24
+ "Shape",
25
+ "If",
26
+ "Unsqueeze",
27
+ "Concat",
28
+ "Add",
29
+ "Where",
30
+ "Less",
31
+ "Sigmoid",
32
+ "Expand",
33
+ "Softmax"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model": {
38
+ "op_types": [
39
+ "Sqrt",
40
+ "Equal",
41
+ "Cast",
42
+ "Mul",
43
+ "Slice",
44
+ "Gather",
45
+ "Constant",
46
+ "ReduceMean",
47
+ "Div",
48
+ "Squeeze",
49
+ "MatMul",
50
+ "ConstantOfShape",
51
+ "Reshape",
52
+ "Pow",
53
+ "Transpose",
54
+ "Range",
55
+ "Sub",
56
+ "Shape",
57
+ "Unsqueeze",
58
+ "Concat",
59
+ "Add",
60
+ "Where",
61
+ "Less",
62
+ "Sigmoid",
63
+ "Expand",
64
+ "Softmax"
65
+ ],
66
+ "weight_type": "QInt8"
67
+ },
68
+ "decoder_with_past_model": {
69
+ "op_types": [
70
+ "Sqrt",
71
+ "Equal",
72
+ "Cast",
73
+ "Mul",
74
+ "Gather",
75
+ "Constant",
76
+ "ReduceMean",
77
+ "Div",
78
+ "MatMul",
79
+ "ConstantOfShape",
80
+ "Reshape",
81
+ "Pow",
82
+ "Transpose",
83
+ "Range",
84
+ "Sub",
85
+ "Shape",
86
+ "Unsqueeze",
87
+ "Concat",
88
+ "Add",
89
+ "Where",
90
+ "Sigmoid",
91
+ "Expand",
92
+ "Softmax"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ },
96
+ "encoder_model": {
97
+ "op_types": [
98
+ "Sqrt",
99
+ "Equal",
100
+ "Cast",
101
+ "Mul",
102
+ "Gather",
103
+ "Constant",
104
+ "ReduceMean",
105
+ "Div",
106
+ "MatMul",
107
+ "ConstantOfShape",
108
+ "Reshape",
109
+ "Pow",
110
+ "Transpose",
111
+ "Range",
112
+ "Sub",
113
+ "Shape",
114
+ "Unsqueeze",
115
+ "Concat",
116
+ "Add",
117
+ "Where",
118
+ "Sigmoid",
119
+ "Expand",
120
+ "Softmax"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (809 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 (756 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": "eng",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "vie",
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