End of training
Browse files- README.md +55 -0
- added_tokens.json +47 -0
- config.json +192 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- preprocessor_config.json +26 -0
- runs/Apr16_07-17-05_B80-C-VMICTGPU01/events.out.tfevents.1713251826.B80-C-VMICTGPU01.3067.1 +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +361 -0
- tokenizer.json +0 -0
- tokenizer_config.json +462 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- imagefolder
|
8 |
+
model-index:
|
9 |
+
- name: PolizzeDonut-CR-Cluster1di7-ConPre-3Epochs
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# PolizzeDonut-CR-Cluster1di7-ConPre-3Epochs
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0](https://huggingface.co/tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0) on the imagefolder dataset.
|
19 |
+
|
20 |
+
## Model description
|
21 |
+
|
22 |
+
More information needed
|
23 |
+
|
24 |
+
## Intended uses & limitations
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Training and evaluation data
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training procedure
|
33 |
+
|
34 |
+
### Training hyperparameters
|
35 |
+
|
36 |
+
The following hyperparameters were used during training:
|
37 |
+
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 2
|
39 |
+
- eval_batch_size: 8
|
40 |
+
- seed: 42
|
41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
+
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 3
|
44 |
+
- mixed_precision_training: Native AMP
|
45 |
+
|
46 |
+
### Training results
|
47 |
+
|
48 |
+
|
49 |
+
|
50 |
+
### Framework versions
|
51 |
+
|
52 |
+
- Transformers 4.38.2
|
53 |
+
- Pytorch 2.2.2+cu121
|
54 |
+
- Datasets 2.18.0
|
55 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s_Consignee_Altro>": 57536,
|
3 |
+
"</s_Consignee_Country>": 57562,
|
4 |
+
"</s_Consignee_Indirizzo>": 57534,
|
5 |
+
"</s_Consignee_RagioneSociale>": 57532,
|
6 |
+
"</s_Consignor_Altro>": 57530,
|
7 |
+
"</s_Consignor_Country>": 57560,
|
8 |
+
"</s_Consignor_Indirizzo>": 57528,
|
9 |
+
"</s_Consignor_RagioneSociale>": 57526,
|
10 |
+
"</s_Goods_Description>": 57550,
|
11 |
+
"</s_Marks>": 57552,
|
12 |
+
"</s_Notify_Altro>": 57542,
|
13 |
+
"</s_Notify_Country>": 57564,
|
14 |
+
"</s_Notify_Indirizzo>": 57540,
|
15 |
+
"</s_Notify_RagioneSociale>": 57538,
|
16 |
+
"</s_Second_Notify_Altro>": 57548,
|
17 |
+
"</s_Second_Notify_Country>": 57566,
|
18 |
+
"</s_Second_Notify_Indirizzo>": 57546,
|
19 |
+
"</s_Second_Notify_RagioneSociale>": 57544,
|
20 |
+
"</s_Total_Packages>": 57554,
|
21 |
+
"</s_Total_Volume>": 57558,
|
22 |
+
"</s_Total_Weight>": 57556,
|
23 |
+
"<s_Consignee_Altro>": 57535,
|
24 |
+
"<s_Consignee_Country>": 57561,
|
25 |
+
"<s_Consignee_Indirizzo>": 57533,
|
26 |
+
"<s_Consignee_RagioneSociale>": 57531,
|
27 |
+
"<s_Consignor_Altro>": 57529,
|
28 |
+
"<s_Consignor_Country>": 57559,
|
29 |
+
"<s_Consignor_Indirizzo>": 57527,
|
30 |
+
"<s_Consignor_RagioneSociale>": 57525,
|
31 |
+
"<s_Goods_Description>": 57549,
|
32 |
+
"<s_Marks>": 57551,
|
33 |
+
"<s_Notify_Altro>": 57541,
|
34 |
+
"<s_Notify_Country>": 57563,
|
35 |
+
"<s_Notify_Indirizzo>": 57539,
|
36 |
+
"<s_Notify_RagioneSociale>": 57537,
|
37 |
+
"<s_Second_Notify_Altro>": 57547,
|
38 |
+
"<s_Second_Notify_Country>": 57565,
|
39 |
+
"<s_Second_Notify_Indirizzo>": 57545,
|
40 |
+
"<s_Second_Notify_RagioneSociale>": 57543,
|
41 |
+
"<s_Total_Packages>": 57553,
|
42 |
+
"<s_Total_Volume>": 57557,
|
43 |
+
"<s_Total_Weight>": 57555,
|
44 |
+
"<s_iitcdip>": 57523,
|
45 |
+
"<s_synthdog>": 57524,
|
46 |
+
"<sep/>": 57522
|
47 |
+
}
|
config.json
ADDED
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tedad09/PolizzeDonut-ChangeRequest-imm5epochs-Expand0",
|
3 |
+
"architectures": [
|
4 |
+
"VisionEncoderDecoderModel"
|
5 |
+
],
|
6 |
+
"decoder": {
|
7 |
+
"_name_or_path": "",
|
8 |
+
"activation_dropout": 0.0,
|
9 |
+
"activation_function": "gelu",
|
10 |
+
"add_cross_attention": true,
|
11 |
+
"add_final_layer_norm": true,
|
12 |
+
"architectures": null,
|
13 |
+
"attention_dropout": 0.0,
|
14 |
+
"bad_words_ids": null,
|
15 |
+
"begin_suppress_tokens": null,
|
16 |
+
"bos_token_id": 0,
|
17 |
+
"chunk_size_feed_forward": 0,
|
18 |
+
"classifier_dropout": 0.0,
|
19 |
+
"cross_attention_hidden_size": null,
|
20 |
+
"d_model": 1024,
|
21 |
+
"decoder_attention_heads": 16,
|
22 |
+
"decoder_ffn_dim": 4096,
|
23 |
+
"decoder_layerdrop": 0.0,
|
24 |
+
"decoder_layers": 4,
|
25 |
+
"decoder_start_token_id": null,
|
26 |
+
"diversity_penalty": 0.0,
|
27 |
+
"do_sample": false,
|
28 |
+
"dropout": 0.1,
|
29 |
+
"early_stopping": false,
|
30 |
+
"encoder_attention_heads": 16,
|
31 |
+
"encoder_ffn_dim": 4096,
|
32 |
+
"encoder_layerdrop": 0.0,
|
33 |
+
"encoder_layers": 12,
|
34 |
+
"encoder_no_repeat_ngram_size": 0,
|
35 |
+
"eos_token_id": 2,
|
36 |
+
"exponential_decay_length_penalty": null,
|
37 |
+
"finetuning_task": null,
|
38 |
+
"forced_bos_token_id": null,
|
39 |
+
"forced_eos_token_id": 2,
|
40 |
+
"id2label": {
|
41 |
+
"0": "LABEL_0",
|
42 |
+
"1": "LABEL_1"
|
43 |
+
},
|
44 |
+
"init_std": 0.02,
|
45 |
+
"is_decoder": true,
|
46 |
+
"is_encoder_decoder": false,
|
47 |
+
"label2id": {
|
48 |
+
"LABEL_0": 0,
|
49 |
+
"LABEL_1": 1
|
50 |
+
},
|
51 |
+
"length_penalty": 1.0,
|
52 |
+
"max_length": 512,
|
53 |
+
"max_position_embeddings": 1536,
|
54 |
+
"min_length": 0,
|
55 |
+
"model_type": "mbart",
|
56 |
+
"no_repeat_ngram_size": 0,
|
57 |
+
"num_beam_groups": 1,
|
58 |
+
"num_beams": 1,
|
59 |
+
"num_hidden_layers": 12,
|
60 |
+
"num_return_sequences": 1,
|
61 |
+
"output_attentions": false,
|
62 |
+
"output_hidden_states": false,
|
63 |
+
"output_scores": false,
|
64 |
+
"pad_token_id": 1,
|
65 |
+
"prefix": null,
|
66 |
+
"problem_type": null,
|
67 |
+
"pruned_heads": {},
|
68 |
+
"remove_invalid_values": false,
|
69 |
+
"repetition_penalty": 1.0,
|
70 |
+
"return_dict": true,
|
71 |
+
"return_dict_in_generate": false,
|
72 |
+
"scale_embedding": true,
|
73 |
+
"sep_token_id": null,
|
74 |
+
"suppress_tokens": null,
|
75 |
+
"task_specific_params": null,
|
76 |
+
"temperature": 1.0,
|
77 |
+
"tf_legacy_loss": false,
|
78 |
+
"tie_encoder_decoder": false,
|
79 |
+
"tie_word_embeddings": true,
|
80 |
+
"tokenizer_class": null,
|
81 |
+
"top_k": 50,
|
82 |
+
"top_p": 1.0,
|
83 |
+
"torch_dtype": null,
|
84 |
+
"torchscript": false,
|
85 |
+
"typical_p": 1.0,
|
86 |
+
"use_bfloat16": false,
|
87 |
+
"use_cache": true,
|
88 |
+
"vocab_size": 57567
|
89 |
+
},
|
90 |
+
"decoder_start_token_id": 0,
|
91 |
+
"encoder": {
|
92 |
+
"_name_or_path": "",
|
93 |
+
"add_cross_attention": false,
|
94 |
+
"architectures": null,
|
95 |
+
"attention_probs_dropout_prob": 0.0,
|
96 |
+
"bad_words_ids": null,
|
97 |
+
"begin_suppress_tokens": null,
|
98 |
+
"bos_token_id": null,
|
99 |
+
"chunk_size_feed_forward": 0,
|
100 |
+
"cross_attention_hidden_size": null,
|
101 |
+
"decoder_start_token_id": null,
|
102 |
+
"depths": [
|
103 |
+
2,
|
104 |
+
2,
|
105 |
+
14,
|
106 |
+
2
|
107 |
+
],
|
108 |
+
"diversity_penalty": 0.0,
|
109 |
+
"do_sample": false,
|
110 |
+
"drop_path_rate": 0.1,
|
111 |
+
"early_stopping": false,
|
112 |
+
"embed_dim": 128,
|
113 |
+
"encoder_no_repeat_ngram_size": 0,
|
114 |
+
"eos_token_id": null,
|
115 |
+
"exponential_decay_length_penalty": null,
|
116 |
+
"finetuning_task": null,
|
117 |
+
"forced_bos_token_id": null,
|
118 |
+
"forced_eos_token_id": null,
|
119 |
+
"hidden_act": "gelu",
|
120 |
+
"hidden_dropout_prob": 0.0,
|
121 |
+
"hidden_size": 1024,
|
122 |
+
"id2label": {
|
123 |
+
"0": "LABEL_0",
|
124 |
+
"1": "LABEL_1"
|
125 |
+
},
|
126 |
+
"image_size": [
|
127 |
+
1286,
|
128 |
+
918
|
129 |
+
],
|
130 |
+
"initializer_range": 0.02,
|
131 |
+
"is_decoder": false,
|
132 |
+
"is_encoder_decoder": false,
|
133 |
+
"label2id": {
|
134 |
+
"LABEL_0": 0,
|
135 |
+
"LABEL_1": 1
|
136 |
+
},
|
137 |
+
"layer_norm_eps": 1e-05,
|
138 |
+
"length_penalty": 1.0,
|
139 |
+
"max_length": 20,
|
140 |
+
"min_length": 0,
|
141 |
+
"mlp_ratio": 4.0,
|
142 |
+
"model_type": "donut-swin",
|
143 |
+
"no_repeat_ngram_size": 0,
|
144 |
+
"num_beam_groups": 1,
|
145 |
+
"num_beams": 1,
|
146 |
+
"num_channels": 3,
|
147 |
+
"num_heads": [
|
148 |
+
4,
|
149 |
+
8,
|
150 |
+
16,
|
151 |
+
32
|
152 |
+
],
|
153 |
+
"num_layers": 4,
|
154 |
+
"num_return_sequences": 1,
|
155 |
+
"output_attentions": false,
|
156 |
+
"output_hidden_states": false,
|
157 |
+
"output_scores": false,
|
158 |
+
"pad_token_id": null,
|
159 |
+
"patch_size": 4,
|
160 |
+
"path_norm": true,
|
161 |
+
"prefix": null,
|
162 |
+
"problem_type": null,
|
163 |
+
"pruned_heads": {},
|
164 |
+
"qkv_bias": true,
|
165 |
+
"remove_invalid_values": false,
|
166 |
+
"repetition_penalty": 1.0,
|
167 |
+
"return_dict": true,
|
168 |
+
"return_dict_in_generate": false,
|
169 |
+
"sep_token_id": null,
|
170 |
+
"suppress_tokens": null,
|
171 |
+
"task_specific_params": null,
|
172 |
+
"temperature": 1.0,
|
173 |
+
"tf_legacy_loss": false,
|
174 |
+
"tie_encoder_decoder": false,
|
175 |
+
"tie_word_embeddings": true,
|
176 |
+
"tokenizer_class": null,
|
177 |
+
"top_k": 50,
|
178 |
+
"top_p": 1.0,
|
179 |
+
"torch_dtype": null,
|
180 |
+
"torchscript": false,
|
181 |
+
"typical_p": 1.0,
|
182 |
+
"use_absolute_embeddings": false,
|
183 |
+
"use_bfloat16": false,
|
184 |
+
"window_size": 10
|
185 |
+
},
|
186 |
+
"is_encoder_decoder": true,
|
187 |
+
"model_type": "vision-encoder-decoder",
|
188 |
+
"pad_token_id": 1,
|
189 |
+
"tie_word_embeddings": false,
|
190 |
+
"torch_dtype": "float32",
|
191 |
+
"transformers_version": "4.38.2"
|
192 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"forced_eos_token_id": 2,
|
6 |
+
"pad_token_id": 1,
|
7 |
+
"transformers_version": "4.38.2"
|
8 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8992381d446a806d5c107997d14937f7d7fbbbaaf0807c810f9c807cef830238
|
3 |
+
size 809242776
|
preprocessor_config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_align_long_axis": false,
|
3 |
+
"do_normalize": true,
|
4 |
+
"do_pad": true,
|
5 |
+
"do_rescale": true,
|
6 |
+
"do_resize": true,
|
7 |
+
"do_thumbnail": true,
|
8 |
+
"image_mean": [
|
9 |
+
0.5,
|
10 |
+
0.5,
|
11 |
+
0.5
|
12 |
+
],
|
13 |
+
"image_processor_type": "DonutImageProcessor",
|
14 |
+
"image_std": [
|
15 |
+
0.5,
|
16 |
+
0.5,
|
17 |
+
0.5
|
18 |
+
],
|
19 |
+
"processor_class": "DonutProcessor",
|
20 |
+
"resample": 2,
|
21 |
+
"rescale_factor": 0.00392156862745098,
|
22 |
+
"size": [
|
23 |
+
918,
|
24 |
+
1286
|
25 |
+
]
|
26 |
+
}
|
runs/Apr16_07-17-05_B80-C-VMICTGPU01/events.out.tfevents.1713251826.B80-C-VMICTGPU01.3067.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c340d277eacaf9775441ffc1b5dee29292a6c07fb94b21be3294616959c96a47
|
3 |
+
size 9433
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
|
3 |
+
size 1296245
|
special_tokens_map.json
ADDED
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<s_Consignor_RagioneSociale>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "</s_Consignor_RagioneSociale>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<s_Consignor_Indirizzo>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "</s_Consignor_Indirizzo>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<s_Consignor_Altro>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "</s_Consignor_Altro>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<s_Consignee_RagioneSociale>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "</s_Consignee_RagioneSociale>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<s_Consignee_Indirizzo>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "</s_Consignee_Indirizzo>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": false,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<s_Consignee_Altro>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": false,
|
77 |
+
"rstrip": false,
|
78 |
+
"single_word": false
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"content": "</s_Consignee_Altro>",
|
82 |
+
"lstrip": false,
|
83 |
+
"normalized": false,
|
84 |
+
"rstrip": false,
|
85 |
+
"single_word": false
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"content": "<s_Notify_RagioneSociale>",
|
89 |
+
"lstrip": false,
|
90 |
+
"normalized": false,
|
91 |
+
"rstrip": false,
|
92 |
+
"single_word": false
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"content": "</s_Notify_RagioneSociale>",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": false,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"content": "<s_Notify_Indirizzo>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"content": "</s_Notify_Indirizzo>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"content": "<s_Notify_Altro>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"content": "</s_Notify_Altro>",
|
124 |
+
"lstrip": false,
|
125 |
+
"normalized": false,
|
126 |
+
"rstrip": false,
|
127 |
+
"single_word": false
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"content": "<s_Second_Notify_RagioneSociale>",
|
131 |
+
"lstrip": false,
|
132 |
+
"normalized": false,
|
133 |
+
"rstrip": false,
|
134 |
+
"single_word": false
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"content": "</s_Second_Notify_RagioneSociale>",
|
138 |
+
"lstrip": false,
|
139 |
+
"normalized": false,
|
140 |
+
"rstrip": false,
|
141 |
+
"single_word": false
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"content": "<s_Second_Notify_Indirizzo>",
|
145 |
+
"lstrip": false,
|
146 |
+
"normalized": false,
|
147 |
+
"rstrip": false,
|
148 |
+
"single_word": false
|
149 |
+
},
|
150 |
+
{
|
151 |
+
"content": "</s_Second_Notify_Indirizzo>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": false,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"content": "<s_Second_Notify_Altro>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"content": "</s_Second_Notify_Altro>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"content": "<s_Goods_Description>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"content": "</s_Goods_Description>",
|
180 |
+
"lstrip": false,
|
181 |
+
"normalized": false,
|
182 |
+
"rstrip": false,
|
183 |
+
"single_word": false
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"content": "<s_Marks>",
|
187 |
+
"lstrip": false,
|
188 |
+
"normalized": false,
|
189 |
+
"rstrip": false,
|
190 |
+
"single_word": false
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"content": "</s_Marks>",
|
194 |
+
"lstrip": false,
|
195 |
+
"normalized": false,
|
196 |
+
"rstrip": false,
|
197 |
+
"single_word": false
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"content": "<s_Total_Packages>",
|
201 |
+
"lstrip": false,
|
202 |
+
"normalized": false,
|
203 |
+
"rstrip": false,
|
204 |
+
"single_word": false
|
205 |
+
},
|
206 |
+
{
|
207 |
+
"content": "</s_Total_Packages>",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": false,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false
|
212 |
+
},
|
213 |
+
{
|
214 |
+
"content": "<s_Total_Weight>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"content": "</s_Total_Weight>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"content": "<s_Total_Volume>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false
|
233 |
+
},
|
234 |
+
{
|
235 |
+
"content": "</s_Total_Volume>",
|
236 |
+
"lstrip": false,
|
237 |
+
"normalized": false,
|
238 |
+
"rstrip": false,
|
239 |
+
"single_word": false
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"content": "<s_Consignor_Country>",
|
243 |
+
"lstrip": false,
|
244 |
+
"normalized": false,
|
245 |
+
"rstrip": false,
|
246 |
+
"single_word": false
|
247 |
+
},
|
248 |
+
{
|
249 |
+
"content": "</s_Consignor_Country>",
|
250 |
+
"lstrip": false,
|
251 |
+
"normalized": false,
|
252 |
+
"rstrip": false,
|
253 |
+
"single_word": false
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"content": "<s_Consignee_Country>",
|
257 |
+
"lstrip": false,
|
258 |
+
"normalized": false,
|
259 |
+
"rstrip": false,
|
260 |
+
"single_word": false
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"content": "</s_Consignee_Country>",
|
264 |
+
"lstrip": false,
|
265 |
+
"normalized": false,
|
266 |
+
"rstrip": false,
|
267 |
+
"single_word": false
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"content": "<s_Notify_Country>",
|
271 |
+
"lstrip": false,
|
272 |
+
"normalized": false,
|
273 |
+
"rstrip": false,
|
274 |
+
"single_word": false
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"content": "</s_Notify_Country>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"content": "<s_Second_Notify_Country>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false
|
289 |
+
},
|
290 |
+
{
|
291 |
+
"content": "</s_Second_Notify_Country>",
|
292 |
+
"lstrip": false,
|
293 |
+
"normalized": false,
|
294 |
+
"rstrip": false,
|
295 |
+
"single_word": false
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"content": "<s>",
|
299 |
+
"lstrip": false,
|
300 |
+
"normalized": false,
|
301 |
+
"rstrip": false,
|
302 |
+
"single_word": false
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"content": "</s>",
|
306 |
+
"lstrip": false,
|
307 |
+
"normalized": false,
|
308 |
+
"rstrip": false,
|
309 |
+
"single_word": false
|
310 |
+
}
|
311 |
+
],
|
312 |
+
"bos_token": {
|
313 |
+
"content": "<s>",
|
314 |
+
"lstrip": false,
|
315 |
+
"normalized": false,
|
316 |
+
"rstrip": false,
|
317 |
+
"single_word": false
|
318 |
+
},
|
319 |
+
"cls_token": {
|
320 |
+
"content": "<s>",
|
321 |
+
"lstrip": false,
|
322 |
+
"normalized": false,
|
323 |
+
"rstrip": false,
|
324 |
+
"single_word": false
|
325 |
+
},
|
326 |
+
"eos_token": {
|
327 |
+
"content": "</s>",
|
328 |
+
"lstrip": false,
|
329 |
+
"normalized": false,
|
330 |
+
"rstrip": false,
|
331 |
+
"single_word": false
|
332 |
+
},
|
333 |
+
"mask_token": {
|
334 |
+
"content": "<mask>",
|
335 |
+
"lstrip": true,
|
336 |
+
"normalized": true,
|
337 |
+
"rstrip": false,
|
338 |
+
"single_word": false
|
339 |
+
},
|
340 |
+
"pad_token": {
|
341 |
+
"content": "<pad>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false
|
346 |
+
},
|
347 |
+
"sep_token": {
|
348 |
+
"content": "</s>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false
|
353 |
+
},
|
354 |
+
"unk_token": {
|
355 |
+
"content": "<unk>",
|
356 |
+
"lstrip": false,
|
357 |
+
"normalized": false,
|
358 |
+
"rstrip": false,
|
359 |
+
"single_word": false
|
360 |
+
}
|
361 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,462 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"57521": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": true,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"57522": {
|
44 |
+
"content": "<sep/>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": true,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": false
|
50 |
+
},
|
51 |
+
"57523": {
|
52 |
+
"content": "<s_iitcdip>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"57524": {
|
60 |
+
"content": "<s_synthdog>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"57525": {
|
68 |
+
"content": "<s_Consignor_RagioneSociale>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"57526": {
|
76 |
+
"content": "</s_Consignor_RagioneSociale>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"57527": {
|
84 |
+
"content": "<s_Consignor_Indirizzo>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"57528": {
|
92 |
+
"content": "</s_Consignor_Indirizzo>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"57529": {
|
100 |
+
"content": "<s_Consignor_Altro>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"57530": {
|
108 |
+
"content": "</s_Consignor_Altro>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"57531": {
|
116 |
+
"content": "<s_Consignee_RagioneSociale>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"57532": {
|
124 |
+
"content": "</s_Consignee_RagioneSociale>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"57533": {
|
132 |
+
"content": "<s_Consignee_Indirizzo>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"57534": {
|
140 |
+
"content": "</s_Consignee_Indirizzo>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"57535": {
|
148 |
+
"content": "<s_Consignee_Altro>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"57536": {
|
156 |
+
"content": "</s_Consignee_Altro>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"57537": {
|
164 |
+
"content": "<s_Notify_RagioneSociale>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"57538": {
|
172 |
+
"content": "</s_Notify_RagioneSociale>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"57539": {
|
180 |
+
"content": "<s_Notify_Indirizzo>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"57540": {
|
188 |
+
"content": "</s_Notify_Indirizzo>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"57541": {
|
196 |
+
"content": "<s_Notify_Altro>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"57542": {
|
204 |
+
"content": "</s_Notify_Altro>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"57543": {
|
212 |
+
"content": "<s_Second_Notify_RagioneSociale>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"57544": {
|
220 |
+
"content": "</s_Second_Notify_RagioneSociale>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"57545": {
|
228 |
+
"content": "<s_Second_Notify_Indirizzo>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"57546": {
|
236 |
+
"content": "</s_Second_Notify_Indirizzo>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"57547": {
|
244 |
+
"content": "<s_Second_Notify_Altro>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"57548": {
|
252 |
+
"content": "</s_Second_Notify_Altro>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"57549": {
|
260 |
+
"content": "<s_Goods_Description>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"57550": {
|
268 |
+
"content": "</s_Goods_Description>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"57551": {
|
276 |
+
"content": "<s_Marks>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"57552": {
|
284 |
+
"content": "</s_Marks>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"57553": {
|
292 |
+
"content": "<s_Total_Packages>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"57554": {
|
300 |
+
"content": "</s_Total_Packages>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"57555": {
|
308 |
+
"content": "<s_Total_Weight>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"57556": {
|
316 |
+
"content": "</s_Total_Weight>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"57557": {
|
324 |
+
"content": "<s_Total_Volume>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"57558": {
|
332 |
+
"content": "</s_Total_Volume>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"57559": {
|
340 |
+
"content": "<s_Consignor_Country>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"57560": {
|
348 |
+
"content": "</s_Consignor_Country>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"57561": {
|
356 |
+
"content": "<s_Consignee_Country>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"57562": {
|
364 |
+
"content": "</s_Consignee_Country>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"57563": {
|
372 |
+
"content": "<s_Notify_Country>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"57564": {
|
380 |
+
"content": "</s_Notify_Country>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"57565": {
|
388 |
+
"content": "<s_Second_Notify_Country>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"57566": {
|
396 |
+
"content": "</s_Second_Notify_Country>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
}
|
403 |
+
},
|
404 |
+
"additional_special_tokens": [
|
405 |
+
"<s_Consignor_RagioneSociale>",
|
406 |
+
"</s_Consignor_RagioneSociale>",
|
407 |
+
"<s_Consignor_Indirizzo>",
|
408 |
+
"</s_Consignor_Indirizzo>",
|
409 |
+
"<s_Consignor_Altro>",
|
410 |
+
"</s_Consignor_Altro>",
|
411 |
+
"<s_Consignee_RagioneSociale>",
|
412 |
+
"</s_Consignee_RagioneSociale>",
|
413 |
+
"<s_Consignee_Indirizzo>",
|
414 |
+
"</s_Consignee_Indirizzo>",
|
415 |
+
"<s_Consignee_Altro>",
|
416 |
+
"</s_Consignee_Altro>",
|
417 |
+
"<s_Notify_RagioneSociale>",
|
418 |
+
"</s_Notify_RagioneSociale>",
|
419 |
+
"<s_Notify_Indirizzo>",
|
420 |
+
"</s_Notify_Indirizzo>",
|
421 |
+
"<s_Notify_Altro>",
|
422 |
+
"</s_Notify_Altro>",
|
423 |
+
"<s_Second_Notify_RagioneSociale>",
|
424 |
+
"</s_Second_Notify_RagioneSociale>",
|
425 |
+
"<s_Second_Notify_Indirizzo>",
|
426 |
+
"</s_Second_Notify_Indirizzo>",
|
427 |
+
"<s_Second_Notify_Altro>",
|
428 |
+
"</s_Second_Notify_Altro>",
|
429 |
+
"<s_Goods_Description>",
|
430 |
+
"</s_Goods_Description>",
|
431 |
+
"<s_Marks>",
|
432 |
+
"</s_Marks>",
|
433 |
+
"<s_Total_Packages>",
|
434 |
+
"</s_Total_Packages>",
|
435 |
+
"<s_Total_Weight>",
|
436 |
+
"</s_Total_Weight>",
|
437 |
+
"<s_Total_Volume>",
|
438 |
+
"</s_Total_Volume>",
|
439 |
+
"<s_Consignor_Country>",
|
440 |
+
"</s_Consignor_Country>",
|
441 |
+
"<s_Consignee_Country>",
|
442 |
+
"</s_Consignee_Country>",
|
443 |
+
"<s_Notify_Country>",
|
444 |
+
"</s_Notify_Country>",
|
445 |
+
"<s_Second_Notify_Country>",
|
446 |
+
"</s_Second_Notify_Country>",
|
447 |
+
"<s>",
|
448 |
+
"</s>"
|
449 |
+
],
|
450 |
+
"bos_token": "<s>",
|
451 |
+
"clean_up_tokenization_spaces": true,
|
452 |
+
"cls_token": "<s>",
|
453 |
+
"eos_token": "</s>",
|
454 |
+
"mask_token": "<mask>",
|
455 |
+
"model_max_length": 1000000000000000019884624838656,
|
456 |
+
"pad_token": "<pad>",
|
457 |
+
"processor_class": "DonutProcessor",
|
458 |
+
"sep_token": "</s>",
|
459 |
+
"sp_model_kwargs": {},
|
460 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
461 |
+
"unk_token": "<unk>"
|
462 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e73e3bdc7e34e48b5899deaca9a7a115423cad5643d22acfd134465962af4c6c
|
3 |
+
size 5112
|