Hugging Face's logo

Xenova
/
opus-mt-bat-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
a45a2a5
•
1 Parent(s): 0bbf76e

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-bat-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
+ 59055
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": 59055,
25
+ "decoder_vocab_size": 59056,
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": 59056,
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": 59055,
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": 59056
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 59055
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 59055,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 59055,
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 sha256:56e1503c9341ab4cc3ecc9865be56fc469661c11ac11ee0e81b06f46cf0a33ed
3
+ size 344351160
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b19a600fdb012fa0b8f342b1ce1b344916fc124fbbd3f742ebc239cf5ba85c9c
3
+ size 344586642
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95050dbf22de26a787fdeef9576381a02b811c803a06ef0a9dbb5d96a133cf6e
3
+ size 87678548
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f63fc4e1ef121b1a49480992bd1d250555676cd394dd05380464ebd30741e45
3
+ size 87307192
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37fa906412afa68e3376fb70e7487fa683d28716cef343febf7f194b8740c23
3
+ size 331700651
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c895353f4cdcfe0d0527b7a6bd5f03bbbc7725d421411ce51399105efb1c0d72
3
+ size 84035728
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee5d79681a4aa73c64d9a5592e6c44dc47a81602de6f3098b31ae186c34b4cbd
3
+ size 197762860
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adbcaf5ad02db63d4dcb2938abcc06e3b615d68e008398dae1a7f30f124a6bcc
3
+ size 49855902
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
+ "ConstantOfShape",
8
+ "Reshape",
9
+ "Pow",
10
+ "Where",
11
+ "Cast",
12
+ "Mul",
13
+ "ReduceMean",
14
+ "Sigmoid",
15
+ "Constant",
16
+ "Div",
17
+ "Expand",
18
+ "Sub",
19
+ "Unsqueeze",
20
+ "Concat",
21
+ "Equal",
22
+ "Softmax",
23
+ "MatMul",
24
+ "Shape",
25
+ "Sqrt",
26
+ "Transpose",
27
+ "Add",
28
+ "Gather",
29
+ "Range"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "ConstantOfShape",
36
+ "Reshape",
37
+ "Pow",
38
+ "Where",
39
+ "Cast",
40
+ "Mul",
41
+ "ReduceMean",
42
+ "Sigmoid",
43
+ "Constant",
44
+ "Div",
45
+ "Expand",
46
+ "Sub",
47
+ "Unsqueeze",
48
+ "Concat",
49
+ "Equal",
50
+ "Softmax",
51
+ "MatMul",
52
+ "Shape",
53
+ "Sqrt",
54
+ "Transpose",
55
+ "Add",
56
+ "Gather",
57
+ "Range"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "ConstantOfShape",
64
+ "Reshape",
65
+ "Pow",
66
+ "Where",
67
+ "Cast",
68
+ "Mul",
69
+ "ReduceMean",
70
+ "Sigmoid",
71
+ "Constant",
72
+ "Div",
73
+ "Expand",
74
+ "Sub",
75
+ "Squeeze",
76
+ "Unsqueeze",
77
+ "Concat",
78
+ "Less",
79
+ "Equal",
80
+ "Softmax",
81
+ "MatMul",
82
+ "Slice",
83
+ "Shape",
84
+ "Sqrt",
85
+ "Transpose",
86
+ "Add",
87
+ "Gather",
88
+ "Range"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "ConstantOfShape",
95
+ "Reshape",
96
+ "Pow",
97
+ "Where",
98
+ "Cast",
99
+ "Mul",
100
+ "ReduceMean",
101
+ "Sigmoid",
102
+ "Constant",
103
+ "Div",
104
+ "Expand",
105
+ "Sub",
106
+ "Squeeze",
107
+ "Unsqueeze",
108
+ "Concat",
109
+ "If",
110
+ "Less",
111
+ "Equal",
112
+ "Softmax",
113
+ "MatMul",
114
+ "Slice",
115
+ "Shape",
116
+ "Sqrt",
117
+ "Transpose",
118
+ "Add",
119
+ "Gather",
120
+ "Range"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (835 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 (803 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": "bat",
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