Hugging Face's logo

Xenova
/
opus-mt-en-ar

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
37e2b39
•
1 Parent(s): 3bd76a9

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-ar",
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
+ 62801
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": 62801,
25
+ "decoder_vocab_size": 62802,
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": 62802,
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": 62801,
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": 62802
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 62801
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 62801,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 62801,
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 sha256:7eb49039a175bc6466ad5307e2b7040c4b914761e2f7c83138a35f4bdba6ff15
3
+ size 359709760
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442cb0cc6ad76aaa284f19d2de626b3b46b6871103fbf93e385305b74633d64a
3
+ size 359945242
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa113495604aebe8357d0274c75fd0fa008f5f255c99995869086bf276f67cd
3
+ size 91548166
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b6b843f0d4b3438b3341451b079c7fafce89c2fc3d6f29ae50e89b57dc14385
3
+ size 91176810
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afb0044dcc5a48d2115fc8efc4e45746beb6853f4422de61991ae2b4cf8fdff
3
+ size 347059251
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bfc93dd0d70f0d022eec33d25b7140f13dfd426cac8a8c290070ad9ee7b98f3
3
+ size 87905346
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec4d2c96f062a310868aeddbed74717109db4a6ceebf9e19dc39208199e59912
3
+ size 205434668
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53c354d87ced44b39085fe8a46a25f09ea4578d442dbce9663f3977228f8a04e
3
+ size 51773854
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
+ "Unsqueeze",
8
+ "Gather",
9
+ "Sub",
10
+ "Expand",
11
+ "Equal",
12
+ "Constant",
13
+ "Add",
14
+ "Sigmoid",
15
+ "Shape",
16
+ "Where",
17
+ "ReduceMean",
18
+ "Reshape",
19
+ "Softmax",
20
+ "MatMul",
21
+ "Sqrt",
22
+ "Pow",
23
+ "Mul",
24
+ "Div",
25
+ "Range",
26
+ "ConstantOfShape",
27
+ "Concat",
28
+ "Cast",
29
+ "Transpose"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "Unsqueeze",
36
+ "Gather",
37
+ "Sub",
38
+ "Expand",
39
+ "Equal",
40
+ "Constant",
41
+ "Add",
42
+ "Sigmoid",
43
+ "Shape",
44
+ "Where",
45
+ "ReduceMean",
46
+ "Reshape",
47
+ "Softmax",
48
+ "MatMul",
49
+ "Sqrt",
50
+ "Pow",
51
+ "Mul",
52
+ "Div",
53
+ "Range",
54
+ "ConstantOfShape",
55
+ "Concat",
56
+ "Cast",
57
+ "Transpose"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "Less",
64
+ "Unsqueeze",
65
+ "Gather",
66
+ "Sub",
67
+ "Expand",
68
+ "Equal",
69
+ "Constant",
70
+ "Add",
71
+ "Sigmoid",
72
+ "Shape",
73
+ "Where",
74
+ "ReduceMean",
75
+ "Reshape",
76
+ "Softmax",
77
+ "MatMul",
78
+ "Sqrt",
79
+ "Pow",
80
+ "Mul",
81
+ "Div",
82
+ "Squeeze",
83
+ "Range",
84
+ "ConstantOfShape",
85
+ "Concat",
86
+ "Cast",
87
+ "Slice",
88
+ "Transpose"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Less",
95
+ "Unsqueeze",
96
+ "Gather",
97
+ "Sub",
98
+ "Expand",
99
+ "Equal",
100
+ "Constant",
101
+ "If",
102
+ "Add",
103
+ "Sigmoid",
104
+ "Shape",
105
+ "Where",
106
+ "ReduceMean",
107
+ "Reshape",
108
+ "Softmax",
109
+ "MatMul",
110
+ "Sqrt",
111
+ "Pow",
112
+ "Mul",
113
+ "Div",
114
+ "Squeeze",
115
+ "Range",
116
+ "ConstantOfShape",
117
+ "Concat",
118
+ "Cast",
119
+ "Slice",
120
+ "Transpose"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (801 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 (917 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": "ara",
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