Hugging Face's logo

Xenova
/
opus-mt-xh-en

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
4a6989d
·
1 Parent(s): b132d8b

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-xh-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
+ 61284
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": 61284,
26
+ "decoder_vocab_size": 61285,
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": 6,
52
+ "num_hidden_layers": 6,
53
+ "pad_token_id": 61284,
54
+ "scale_embedding": true,
55
+ "share_encoder_decoder_embeddings": true,
56
+ "static_position_embeddings": true,
57
+ "transformers_version": "4.34.0.dev0",
58
+ "use_cache": true,
59
+ "vocab_size": 61285
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bad_words_ids": [
3
+ [
4
+ 61284
5
+ ]
6
+ ],
7
+ "bos_token_id": 0,
8
+ "decoder_start_token_id": 61284,
9
+ "eos_token_id": 0,
10
+ "forced_eos_token_id": 0,
11
+ "max_length": 512,
12
+ "num_beams": 6,
13
+ "pad_token_id": 61284,
14
+ "renormalize_logits": true,
15
+ "transformers_version": "4.34.0.dev0"
16
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:611ee7ff11cf211eb768fbe753ebaf889cc5d47184b19f801ada5a93f1555c4a
3
+ size 227978437
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2e07050da16646a469387b61e632c9d097475313183edb18fa93e3beac192fd
3
+ size 228214004
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d6680c914bf98c26f26a856160e1fdeb8e48a1cc0119507fba63e45a3347da
3
+ size 58295348
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdbab46acf9b6cacc4f30c701dc3532e1909512a73fe3694b23552cdc7b72bae
3
+ size 57924646
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ee5a1335f1bf0e44a571f6b9c64ac460e90bff4537254d73ac75a197fb7620f
3
+ size 215327928
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11350e1145d43b78c81bc5f1bdfff143d4852d2fb4048574035d36057c326726
3
+ size 54653182
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4119eb5fdf6e2ad5ee60c6012653594bd93a089d2cb7a0a3786dd6d79ec1a853
3
+ size 202327852
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91340a48fd07ef1afbd5c185c63de983abf98b2c2b62f1814429a37f73b00a01
3
+ size 50997150
quantize_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Slice",
8
+ "Softmax",
9
+ "Equal",
10
+ "Reshape",
11
+ "Shape",
12
+ "Constant",
13
+ "Expand",
14
+ "Add",
15
+ "Transpose",
16
+ "Range",
17
+ "Sigmoid",
18
+ "Squeeze",
19
+ "Mul",
20
+ "Where",
21
+ "Cast",
22
+ "ConstantOfShape",
23
+ "Div",
24
+ "Concat",
25
+ "Sub",
26
+ "Unsqueeze",
27
+ "Less",
28
+ "MatMul",
29
+ "Sqrt",
30
+ "ReduceMean",
31
+ "Gather",
32
+ "Pow"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "encoder_model": {
37
+ "op_types": [
38
+ "Softmax",
39
+ "Equal",
40
+ "Reshape",
41
+ "Shape",
42
+ "Constant",
43
+ "Expand",
44
+ "Transpose",
45
+ "Add",
46
+ "Range",
47
+ "Sigmoid",
48
+ "Where",
49
+ "Mul",
50
+ "Cast",
51
+ "ConstantOfShape",
52
+ "Div",
53
+ "Concat",
54
+ "Sub",
55
+ "Unsqueeze",
56
+ "MatMul",
57
+ "Sqrt",
58
+ "ReduceMean",
59
+ "Gather",
60
+ "Pow"
61
+ ],
62
+ "weight_type": "QInt8"
63
+ },
64
+ "decoder_model_merged": {
65
+ "op_types": [
66
+ "Slice",
67
+ "Softmax",
68
+ "Equal",
69
+ "Reshape",
70
+ "Shape",
71
+ "Constant",
72
+ "Expand",
73
+ "Add",
74
+ "Transpose",
75
+ "Range",
76
+ "Sigmoid",
77
+ "Squeeze",
78
+ "Mul",
79
+ "Where",
80
+ "Cast",
81
+ "ConstantOfShape",
82
+ "Div",
83
+ "If",
84
+ "Concat",
85
+ "Sub",
86
+ "Unsqueeze",
87
+ "Less",
88
+ "MatMul",
89
+ "Sqrt",
90
+ "ReduceMean",
91
+ "Gather",
92
+ "Pow"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ },
96
+ "decoder_with_past_model": {
97
+ "op_types": [
98
+ "Softmax",
99
+ "Equal",
100
+ "Reshape",
101
+ "Shape",
102
+ "Constant",
103
+ "Expand",
104
+ "Transpose",
105
+ "Add",
106
+ "Range",
107
+ "Sigmoid",
108
+ "Where",
109
+ "Mul",
110
+ "Cast",
111
+ "ConstantOfShape",
112
+ "Div",
113
+ "Concat",
114
+ "Sub",
115
+ "Unsqueeze",
116
+ "MatMul",
117
+ "Sqrt",
118
+ "ReduceMean",
119
+ "Gather",
120
+ "Pow"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (814 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 (819 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": "xh",
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