Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- config.json +60 -0
- generation_config.json +16 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +3 -0
- onnx/decoder_model_quantized.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/encoder_model_quantized.onnx +3 -0
- quantize_config.json +125 -0
- source.spm +3 -0
- special_tokens_map.json +5 -0
- target.spm +0 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
source.spm filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-ru-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 |
+
62517
|
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": 62517,
|
26 |
+
"decoder_vocab_size": 62518,
|
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": 62517,
|
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": 62518
|
60 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bad_words_ids": [
|
4 |
+
[
|
5 |
+
62517
|
6 |
+
]
|
7 |
+
],
|
8 |
+
"bos_token_id": 0,
|
9 |
+
"decoder_start_token_id": 62517,
|
10 |
+
"eos_token_id": 0,
|
11 |
+
"forced_eos_token_id": 0,
|
12 |
+
"max_length": 512,
|
13 |
+
"num_beams": 6,
|
14 |
+
"pad_token_id": 62517,
|
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 sha256:25e2daca91185fe64df60b906ed71bf1502c5ca29e5e70bf1f19dc750066f034
|
3 |
+
size 358545360
|
onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072efcc952c404ab36ed1c0a263fed685573c3b8152cf4564ffdb608098beaf1
|
3 |
+
size 358780842
|
onnx/decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b93089bee18c64446b7598da94e6020cba9035a8bcf9d11e139c92f5c86a1a10
|
3 |
+
size 91254794
|
onnx/decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac7d18a85c33d369d4620264daae4ff009db5cd145f0dbaefb7a4f3fd90e062f
|
3 |
+
size 90883438
|
onnx/decoder_with_past_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7662f473d602635384d9c812d1c99c1375177ffe5db492b8d9c63b6eb2c1974d
|
3 |
+
size 345894851
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4382e6649711360ee7a041aa2171fb44c820c458b9fa7090e1181b5f230cc2b6
|
3 |
+
size 87611974
|
onnx/encoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0663f554a1dc9db914d8ca30fd779803bc5f41a5cd41acd838130be2f41eedeb
|
3 |
+
size 204853036
|
onnx/encoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c10df0466540534bb70c4402d539c349b8bfa9968184cad89f51408cf13e7eb7
|
3 |
+
size 51628446
|
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 |
+
"Cast",
|
8 |
+
"Softmax",
|
9 |
+
"Transpose",
|
10 |
+
"Sigmoid",
|
11 |
+
"Sub",
|
12 |
+
"Unsqueeze",
|
13 |
+
"Div",
|
14 |
+
"Concat",
|
15 |
+
"Range",
|
16 |
+
"Where",
|
17 |
+
"Shape",
|
18 |
+
"MatMul",
|
19 |
+
"Mul",
|
20 |
+
"ConstantOfShape",
|
21 |
+
"Reshape",
|
22 |
+
"Pow",
|
23 |
+
"Equal",
|
24 |
+
"Sqrt",
|
25 |
+
"Gather",
|
26 |
+
"Add",
|
27 |
+
"Constant",
|
28 |
+
"Expand",
|
29 |
+
"ReduceMean"
|
30 |
+
],
|
31 |
+
"weight_type": "QInt8"
|
32 |
+
},
|
33 |
+
"decoder_with_past_model": {
|
34 |
+
"op_types": [
|
35 |
+
"Cast",
|
36 |
+
"Softmax",
|
37 |
+
"Transpose",
|
38 |
+
"Sigmoid",
|
39 |
+
"Sub",
|
40 |
+
"Unsqueeze",
|
41 |
+
"Div",
|
42 |
+
"Concat",
|
43 |
+
"Range",
|
44 |
+
"Where",
|
45 |
+
"Shape",
|
46 |
+
"MatMul",
|
47 |
+
"Mul",
|
48 |
+
"ConstantOfShape",
|
49 |
+
"Reshape",
|
50 |
+
"Pow",
|
51 |
+
"Equal",
|
52 |
+
"Sqrt",
|
53 |
+
"Gather",
|
54 |
+
"Add",
|
55 |
+
"Constant",
|
56 |
+
"Expand",
|
57 |
+
"ReduceMean"
|
58 |
+
],
|
59 |
+
"weight_type": "QInt8"
|
60 |
+
},
|
61 |
+
"decoder_model": {
|
62 |
+
"op_types": [
|
63 |
+
"Cast",
|
64 |
+
"Softmax",
|
65 |
+
"Squeeze",
|
66 |
+
"Transpose",
|
67 |
+
"Sigmoid",
|
68 |
+
"Sub",
|
69 |
+
"Unsqueeze",
|
70 |
+
"Div",
|
71 |
+
"Concat",
|
72 |
+
"Range",
|
73 |
+
"Where",
|
74 |
+
"Slice",
|
75 |
+
"Shape",
|
76 |
+
"MatMul",
|
77 |
+
"Less",
|
78 |
+
"Mul",
|
79 |
+
"ConstantOfShape",
|
80 |
+
"Reshape",
|
81 |
+
"Pow",
|
82 |
+
"Equal",
|
83 |
+
"Sqrt",
|
84 |
+
"Gather",
|
85 |
+
"Add",
|
86 |
+
"Constant",
|
87 |
+
"Expand",
|
88 |
+
"ReduceMean"
|
89 |
+
],
|
90 |
+
"weight_type": "QInt8"
|
91 |
+
},
|
92 |
+
"decoder_model_merged": {
|
93 |
+
"op_types": [
|
94 |
+
"Cast",
|
95 |
+
"Softmax",
|
96 |
+
"Squeeze",
|
97 |
+
"Transpose",
|
98 |
+
"Sigmoid",
|
99 |
+
"Sub",
|
100 |
+
"Unsqueeze",
|
101 |
+
"If",
|
102 |
+
"Div",
|
103 |
+
"Concat",
|
104 |
+
"Range",
|
105 |
+
"Where",
|
106 |
+
"Slice",
|
107 |
+
"Shape",
|
108 |
+
"MatMul",
|
109 |
+
"Less",
|
110 |
+
"Mul",
|
111 |
+
"ConstantOfShape",
|
112 |
+
"Reshape",
|
113 |
+
"Pow",
|
114 |
+
"Equal",
|
115 |
+
"Sqrt",
|
116 |
+
"Gather",
|
117 |
+
"Add",
|
118 |
+
"Constant",
|
119 |
+
"Expand",
|
120 |
+
"ReduceMean"
|
121 |
+
],
|
122 |
+
"weight_type": "QInt8"
|
123 |
+
}
|
124 |
+
}
|
125 |
+
}
|
source.spm
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
|
3 |
+
size 1080169
|
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": "ru",
|
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
|
|