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 +0 -0
- special_tokens_map.json +5 -0
- target.spm +3 -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 |
+
target.spm filter=lfs diff=lfs merge=lfs -text
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Helsinki-NLP/opus-mt-en-jap",
|
| 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 |
+
46275
|
| 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": 46275,
|
| 26 |
+
"decoder_vocab_size": 46276,
|
| 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": 46275,
|
| 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": 46276
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bad_words_ids": [
|
| 3 |
+
[
|
| 4 |
+
46275
|
| 5 |
+
]
|
| 6 |
+
],
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"decoder_start_token_id": 46275,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"forced_eos_token_id": 0,
|
| 11 |
+
"max_length": 512,
|
| 12 |
+
"num_beams": 4,
|
| 13 |
+
"pad_token_id": 46275,
|
| 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 sha256:76cebaa1b29676d73fd3979366c44f5290e171bfef565a8a6be78630b61ef9a0
|
| 3 |
+
size 197179969
|
onnx/decoder_model_merged.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5252acc70dd17b5cf1e26a60a5575c7354d759c05a115ab417b61399b87298b2
|
| 3 |
+
size 197415536
|
onnx/decoder_model_merged_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:084c7544b640eeea722b4858328f479d804236b916a2bec761442ff062726619
|
| 3 |
+
size 50550704
|
onnx/decoder_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b0d117484d2bb22113428f0ab39b24ae3e753d1986ae399c22ff9f102e106b9
|
| 3 |
+
size 50180002
|
onnx/decoder_with_past_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3ee89750fdf8aa07614193a0d4fb2e7a2d5bcd6391c62b99c109d0e1fd5b895
|
| 3 |
+
size 184529460
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da221c434fca8a4a29b9b63f65696afd42df5f5a2042d866d61a2e163a42d659
|
| 3 |
+
size 46908538
|
onnx/encoder_model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04bc882345dc5ec25e191fbb50b98fa14ca824d4d7b45a35a7fdd2f228cd3899
|
| 3 |
+
size 171589420
|
onnx/encoder_model_quantized.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4062a86cbec1d388e779294f07b784179d87a648c90771e94879b3a28cd96be7
|
| 3 |
+
size 43312542
|
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 |
+
"Mul",
|
| 8 |
+
"Sub",
|
| 9 |
+
"Shape",
|
| 10 |
+
"Squeeze",
|
| 11 |
+
"ConstantOfShape",
|
| 12 |
+
"Pow",
|
| 13 |
+
"MatMul",
|
| 14 |
+
"Constant",
|
| 15 |
+
"Div",
|
| 16 |
+
"Range",
|
| 17 |
+
"ReduceMean",
|
| 18 |
+
"Cast",
|
| 19 |
+
"Add",
|
| 20 |
+
"Sqrt",
|
| 21 |
+
"Where",
|
| 22 |
+
"Reshape",
|
| 23 |
+
"Gather",
|
| 24 |
+
"Concat",
|
| 25 |
+
"Equal",
|
| 26 |
+
"Unsqueeze",
|
| 27 |
+
"Slice",
|
| 28 |
+
"Sigmoid",
|
| 29 |
+
"Expand",
|
| 30 |
+
"Less",
|
| 31 |
+
"Softmax",
|
| 32 |
+
"Transpose"
|
| 33 |
+
],
|
| 34 |
+
"weight_type": "QInt8"
|
| 35 |
+
},
|
| 36 |
+
"encoder_model": {
|
| 37 |
+
"op_types": [
|
| 38 |
+
"Mul",
|
| 39 |
+
"Sub",
|
| 40 |
+
"Shape",
|
| 41 |
+
"ConstantOfShape",
|
| 42 |
+
"Pow",
|
| 43 |
+
"MatMul",
|
| 44 |
+
"Constant",
|
| 45 |
+
"Div",
|
| 46 |
+
"Range",
|
| 47 |
+
"ReduceMean",
|
| 48 |
+
"Cast",
|
| 49 |
+
"Add",
|
| 50 |
+
"Sqrt",
|
| 51 |
+
"Where",
|
| 52 |
+
"Reshape",
|
| 53 |
+
"Gather",
|
| 54 |
+
"Concat",
|
| 55 |
+
"Equal",
|
| 56 |
+
"Unsqueeze",
|
| 57 |
+
"Sigmoid",
|
| 58 |
+
"Expand",
|
| 59 |
+
"Softmax",
|
| 60 |
+
"Transpose"
|
| 61 |
+
],
|
| 62 |
+
"weight_type": "QInt8"
|
| 63 |
+
},
|
| 64 |
+
"decoder_model_merged": {
|
| 65 |
+
"op_types": [
|
| 66 |
+
"Mul",
|
| 67 |
+
"Sub",
|
| 68 |
+
"Shape",
|
| 69 |
+
"Squeeze",
|
| 70 |
+
"ConstantOfShape",
|
| 71 |
+
"Pow",
|
| 72 |
+
"MatMul",
|
| 73 |
+
"Constant",
|
| 74 |
+
"Div",
|
| 75 |
+
"Range",
|
| 76 |
+
"ReduceMean",
|
| 77 |
+
"Cast",
|
| 78 |
+
"Add",
|
| 79 |
+
"Sqrt",
|
| 80 |
+
"Where",
|
| 81 |
+
"Reshape",
|
| 82 |
+
"Gather",
|
| 83 |
+
"Concat",
|
| 84 |
+
"Equal",
|
| 85 |
+
"Unsqueeze",
|
| 86 |
+
"If",
|
| 87 |
+
"Slice",
|
| 88 |
+
"Sigmoid",
|
| 89 |
+
"Expand",
|
| 90 |
+
"Less",
|
| 91 |
+
"Softmax",
|
| 92 |
+
"Transpose"
|
| 93 |
+
],
|
| 94 |
+
"weight_type": "QInt8"
|
| 95 |
+
},
|
| 96 |
+
"decoder_with_past_model": {
|
| 97 |
+
"op_types": [
|
| 98 |
+
"Mul",
|
| 99 |
+
"Sub",
|
| 100 |
+
"Shape",
|
| 101 |
+
"ConstantOfShape",
|
| 102 |
+
"Pow",
|
| 103 |
+
"MatMul",
|
| 104 |
+
"Constant",
|
| 105 |
+
"Div",
|
| 106 |
+
"Range",
|
| 107 |
+
"ReduceMean",
|
| 108 |
+
"Cast",
|
| 109 |
+
"Add",
|
| 110 |
+
"Sqrt",
|
| 111 |
+
"Where",
|
| 112 |
+
"Reshape",
|
| 113 |
+
"Gather",
|
| 114 |
+
"Concat",
|
| 115 |
+
"Equal",
|
| 116 |
+
"Unsqueeze",
|
| 117 |
+
"Sigmoid",
|
| 118 |
+
"Expand",
|
| 119 |
+
"Softmax",
|
| 120 |
+
"Transpose"
|
| 121 |
+
],
|
| 122 |
+
"weight_type": "QInt8"
|
| 123 |
+
}
|
| 124 |
+
}
|
| 125 |
+
}
|
source.spm
ADDED
|
Binary file (509 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
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d5ec21daca7dccb7a9df371b699def40ddd9d0c24cef855e44e31a39b96af55
|
| 3 |
+
size 1021944
|
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": "en",
|
| 8 |
+
"sp_model_kwargs": {},
|
| 9 |
+
"target_lang": "jap",
|
| 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
|
|
|