Hugging Face's logo

Xenova
/
opus-mt-gmw-gmw

Translation
Transformers.js
ONNX
marian
text2text-generation
Model card Files Community
Xenova HF staff commited on
Commit
70f1606
·
1 Parent(s): 4314490

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-gmw-gmw",
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
+ 35463
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": 35463,
25
+ "decoder_vocab_size": 35464,
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": 35464,
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": 35463,
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": 35464
60
+ }
generation_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bad_words_ids": [
4
+ [
5
+ 35463
6
+ ]
7
+ ],
8
+ "bos_token_id": 0,
9
+ "decoder_start_token_id": 35463,
10
+ "eos_token_id": 0,
11
+ "forced_eos_token_id": 0,
12
+ "max_length": 512,
13
+ "num_beams": 4,
14
+ "pad_token_id": 35463,
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 sha256:906d24158b6abfff73d3f3a9477d8774581e9008599b149a931b17f683b07297
3
+ size 247623959
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14b770d42c0f0473d701b621e0eabafbd265f0d9a8f235ca54c2e974c71df3e
3
+ size 247859441
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ff747091aa9705f539cb2bac07d05c372e4fea14d1416737110a5d603317999
3
+ size 63308012
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbabbde316b1324624889f16dd8a3a55d5930ac51c3780be63a1b1591cd1349
3
+ size 62936656
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfcec3347c1201a5692f1b5e83d3d4657b48177d40a0ab760e39a34ca2d6c705
3
+ size 234973450
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b580c5bba606c6e74f6496e56687bf722882d7e56f09cac19c22b87352232ce1
3
+ size 59665192
onnx/encoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf33cb6a3ed8f96726d3dea7432cbe6a5e14a2f6cf52af528f870554757e91a
3
+ size 149446444
onnx/encoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26c5ab898ea9d6feb00fc8aa47194fef1f83e441ab24b395fb1dcc5dcdb69fc
3
+ size 37776798
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
+ "Equal",
8
+ "Shape",
9
+ "Concat",
10
+ "Where",
11
+ "ConstantOfShape",
12
+ "Reshape",
13
+ "Div",
14
+ "Softmax",
15
+ "Sigmoid",
16
+ "Transpose",
17
+ "Sqrt",
18
+ "Expand",
19
+ "Cast",
20
+ "Gather",
21
+ "Constant",
22
+ "Unsqueeze",
23
+ "Sub",
24
+ "Range",
25
+ "ReduceMean",
26
+ "Mul",
27
+ "Add",
28
+ "MatMul",
29
+ "Pow"
30
+ ],
31
+ "weight_type": "QInt8"
32
+ },
33
+ "decoder_with_past_model": {
34
+ "op_types": [
35
+ "Equal",
36
+ "Shape",
37
+ "Concat",
38
+ "Where",
39
+ "ConstantOfShape",
40
+ "Reshape",
41
+ "Div",
42
+ "Softmax",
43
+ "Sigmoid",
44
+ "Transpose",
45
+ "Sqrt",
46
+ "Expand",
47
+ "Cast",
48
+ "Gather",
49
+ "Constant",
50
+ "Unsqueeze",
51
+ "Sub",
52
+ "Range",
53
+ "ReduceMean",
54
+ "Mul",
55
+ "Add",
56
+ "MatMul",
57
+ "Pow"
58
+ ],
59
+ "weight_type": "QInt8"
60
+ },
61
+ "decoder_model": {
62
+ "op_types": [
63
+ "Equal",
64
+ "Shape",
65
+ "Concat",
66
+ "Slice",
67
+ "Where",
68
+ "ConstantOfShape",
69
+ "Reshape",
70
+ "Div",
71
+ "Squeeze",
72
+ "Softmax",
73
+ "Sigmoid",
74
+ "Transpose",
75
+ "Sqrt",
76
+ "Expand",
77
+ "Cast",
78
+ "Gather",
79
+ "Constant",
80
+ "Less",
81
+ "Unsqueeze",
82
+ "Sub",
83
+ "Range",
84
+ "ReduceMean",
85
+ "Mul",
86
+ "Add",
87
+ "MatMul",
88
+ "Pow"
89
+ ],
90
+ "weight_type": "QInt8"
91
+ },
92
+ "decoder_model_merged": {
93
+ "op_types": [
94
+ "Equal",
95
+ "Shape",
96
+ "Concat",
97
+ "Slice",
98
+ "Where",
99
+ "ConstantOfShape",
100
+ "Reshape",
101
+ "Div",
102
+ "Squeeze",
103
+ "If",
104
+ "Softmax",
105
+ "Sigmoid",
106
+ "Transpose",
107
+ "Sqrt",
108
+ "Expand",
109
+ "Cast",
110
+ "Gather",
111
+ "Constant",
112
+ "Less",
113
+ "Unsqueeze",
114
+ "Sub",
115
+ "Range",
116
+ "ReduceMean",
117
+ "Mul",
118
+ "Add",
119
+ "MatMul",
120
+ "Pow"
121
+ ],
122
+ "weight_type": "QInt8"
123
+ }
124
+ }
125
+ }
source.spm ADDED
Binary file (802 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": "gmw",
8
+ "sp_model_kwargs": {},
9
+ "target_lang": "gmw",
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