Hugging Face's logo

Xenova
/
opus-mt-ar-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
2
Xenova HF staff commited on
Commit
c6a57f6
•
1 Parent(s): bc69da8

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-ar-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
+ 62833
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": 62833,
26
+ "decoder_vocab_size": 62834,
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": 4,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 62833,
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": 62834
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 62833
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 62833,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 62833,
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 sha256:125b42cc04865b0ff6e64b247a845e45ae1a4b0d45db72d14f1963fbe4508522
3
+ size 359840960
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d67cfd1baf59398a90885ae42e9a4f1cd7cf2c4e2c6a2eb82f2aaab694762b0a
3
+ size 360076442
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e754c5f68327792694e2cf073e5de0b790de019de467017ec44cc31bff17d12d
3
+ size 91581222
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f15ee20988afb1e97c8557a91744d3c41c03acf3c91f1319d0a522e1def20f3
3
+ size 91209866
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1c55d8d96d15be9a0870ddd7e46702a238fd3fd011c46c72ba2c37268b22d95
3
+ size 347190451
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c44860e389b88e49c401ec26b70667038d46f2f184efe49fcafc43a3753d46
3
+ size 87938402
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e32a06d492e9c8e909f96c7ef1dfbbb86199ec506b66ec27f6655eebeac5b2b
3
+ size 205500204
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b0d612acff86cf87634b49bda566d1ef39b312837de549786ea18fecefc708
3
+ size 51790238
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
+ "Mul",
8
+ "MatMul",
9
+ "Cast",
10
+ "Pow",
11
+ "Sub",
12
+ "Sigmoid",
13
+ "ReduceMean",
14
+ "Where",
15
+ "Transpose",
16
+ "Unsqueeze",
17
+ "Expand",
18
+ "Sqrt",
19
+ "Add",
20
+ "Constant",
21
+ "Shape",
22
+ "Concat",
23
+ "Reshape",
24
+ "Div",
25
+ "Equal",
26
+ "Range",
27
+ "ConstantOfShape",
28
+ "Softmax",
29
+ "Gather"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "Mul",
36
+ "MatMul",
37
+ "Cast",
38
+ "Pow",
39
+ "Sub",
40
+ "Sigmoid",
41
+ "ReduceMean",
42
+ "Where",
43
+ "Transpose",
44
+ "Unsqueeze",
45
+ "Expand",
46
+ "Sqrt",
47
+ "Add",
48
+ "Constant",
49
+ "Shape",
50
+ "Concat",
51
+ "Reshape",
52
+ "Div",
53
+ "Equal",
54
+ "Range",
55
+ "ConstantOfShape",
56
+ "Softmax",
57
+ "Gather"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "Mul",
64
+ "MatMul",
65
+ "Cast",
66
+ "Pow",
67
+ "Sub",
68
+ "Sigmoid",
69
+ "ReduceMean",
70
+ "Less",
71
+ "Where",
72
+ "Slice",
73
+ "Transpose",
74
+ "Unsqueeze",
75
+ "Expand",
76
+ "Sqrt",
77
+ "Squeeze",
78
+ "Add",
79
+ "Constant",
80
+ "Shape",
81
+ "Concat",
82
+ "Reshape",
83
+ "Div",
84
+ "Equal",
85
+ "Range",
86
+ "ConstantOfShape",
87
+ "Softmax",
88
+ "Gather"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Mul",
95
+ "MatMul",
96
+ "Cast",
97
+ "Pow",
98
+ "Sub",
99
+ "Sigmoid",
100
+ "ReduceMean",
101
+ "Less",
102
+ "Where",
103
+ "Slice",
104
+ "Transpose",
105
+ "Unsqueeze",
106
+ "Expand",
107
+ "Sqrt",
108
+ "Squeeze",
109
+ "Add",
110
+ "If",
111
+ "Constant",
112
+ "Shape",
113
+ "Concat",
114
+ "Reshape",
115
+ "Div",
116
+ "Equal",
117
+ "Range",
118
+ "ConstantOfShape",
119
+ "Softmax",
120
+ "Gather"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (917 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": "ar",
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