Maldopast commited on
Commit
24648c0
1 Parent(s): a5dff1a

Upload TextClassificationPipeline

Browse files
README.md ADDED
@@ -0,0 +1,199 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags: []
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+ This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
config.json ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "models/mvid_deep_vk_bge_ecom_18_8_0.1_5e-05_1e-06_text_mark_st_weights_valid_in_train",
3
+ "architectures": [
4
+ "XLMRobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "\u0414\u043e\u043b\u0433\u0430\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0430",
15
+ "1": "\u0414\u043e\u0441\u0442\u0430\u0432\u043a\u0430 \u0441\u0442\u0430\u043b\u0430 \u0434\u043e\u043b\u0433\u043e\u0439",
16
+ "2": "\u0412\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438 \u043d\u0435 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u0435\u0442 \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u043e\u043c\u0443",
17
+ "3": "\u0420\u0435\u0433\u0443\u043b\u044f\u0440\u043d\u044b\u0435 \u043e\u043f\u043e\u0437\u0434\u0430\u043d\u0438\u044f",
18
+ "4": "\u041d\u0435 \u043e\u0442\u0441\u043b\u0435\u0434\u0438\u0442\u044c \u0440\u0435\u0430\u043b\u044c\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438",
19
+ "5": "\u041a\u0443\u0440\u044c\u0435\u0440 \u043d\u0430 \u043a\u0430\u0440\u0442\u0435",
20
+ "6": "\u041d\u0435\u0442 \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438 \u043f\u043e \u0430\u0434\u0440\u0435\u0441\u0443",
21
+ "7": "\u041d\u0435 \u043f\u0440\u0435\u0434\u0443\u043f\u0440\u0435\u0436\u0434\u0430\u0435\u043c \u043e\u0431 \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u0438 \u0442\u043e\u0432\u0430\u0440\u0430",
22
+ "8": "\u0412\u044b\u0441\u043e\u043a\u0430\u044f \u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f \u0441\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430",
23
+ "9": "\u0421\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430 \u043c\u0435\u043d\u044f\u0435\u0442\u0441\u044f \u0432\u043e \u0432\u0440\u0435\u043c\u044f \u043d\u0430\u0431\u043e\u0440\u0430 \u043a\u043e\u0440\u0437\u0438\u043d\u044b",
24
+ "10": "\u041c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f \u0441\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430",
25
+ "11": "\u0422\u043e\u0432\u0430\u0440\u044b \u0441 \u043f\u043e\u0434\u0445\u043e\u0434\u044f\u0449\u0438\u043c \u0441\u0440\u043e\u043a\u043e\u043c \u0433\u043e\u0434\u043d\u043e\u0441\u0442\u0438",
26
+ "12": "\u0412\u044b\u0441\u043e\u043a\u0438\u0435 \u0446\u0435\u043d\u044b",
27
+ "13": "\u041d\u0435 \u0434\u043e\u0432\u0435\u0437\u043b\u0438 \u0442\u043e\u0432\u0430\u0440",
28
+ "14": "\u0422\u043e\u0432\u0430\u0440 \u0438\u0441\u043f\u043e\u0440\u0447\u0435\u043d \u0432\u043e \u0432\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438",
29
+ "15": "\u041f\u0440\u043e\u0441\u0440\u043e\u0447\u0435\u043d\u043d\u044b\u0435 \u0442\u043e\u0432\u0430\u0440\u044b",
30
+ "16": "\u0417\u0430\u043c\u0435\u0447\u0430\u043d\u0438\u044f \u043f\u043e \u0440\u0430\u0431\u043e\u0442\u0435 \u043a\u0443\u0440\u044c\u0435\u0440\u043e\u0432",
31
+ "17": "\u041d\u0435 \u0447\u0438\u0442\u0430\u0435\u043c \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0438",
32
+ "18": "\u0421\u043f\u0430\u0441\u0438\u0431\u043e",
33
+ "19": "\u041d\u0435\u0442 \u0441\u043c\u044b\u0441\u043b\u0430",
34
+ "20": "\u0412\u0441\u0451 \u043d\u043e\u0440\u043c\u0430\u043b\u044c\u043d\u043e",
35
+ "21": "\u0412\u0441\u0451 \u043f\u043b\u043e\u0445\u043e",
36
+ "22": "\u0421\u043a\u0438\u0434\u043a\u0438 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0445 \u043a\u043b\u0438\u0435\u043d\u0442\u043e\u0432",
37
+ "23": "\u0411\u043e\u043b\u044c\u0448\u0435 \u0430\u043a\u0446\u0438\u0439/\u0441\u043a\u0438\u0434\u043e\u043a",
38
+ "24": "\u0421\u043a\u0438\u0434\u043a\u0430/\u043f\u0440\u043e\u043c\u043e\u043a\u043e\u0434 \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u0435\u0442\u0441\u044f \u043d\u0435 \u043d\u0430 \u0432\u0441\u0435 \u0442\u043e\u0432\u0430\u0440\u044b",
39
+ "25": "\u041d\u0435\u043f\u043e\u043d\u044f\u0442\u043d\u043e \u043a\u0430\u043a \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u0441\u043a\u0438\u0434\u043a\u0430",
40
+ "26": "\u041d\u0435 \u0441\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0430 \u0441\u043a\u0438\u0434\u043a\u0430/\u0430\u043a\u0446\u0438\u044f/\u043f\u0440\u043e\u043c\u043e\u043a\u043e\u0434",
41
+ "27": "\u041a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u0432\u0430\u0440\u043e\u0432",
42
+ "28": "\u041c\u0430\u043b\u0435\u043d\u044c\u043a\u0438\u0439 \u0430\u0441\u0441\u043e\u0440\u0442\u0438\u043c\u0435\u043d\u0442",
43
+ "29": "\u041d\u0435\u0442 \u0432 \u043d\u0430\u043b\u0438\u0447\u0438\u0438 \u0442\u043e\u0432\u0430\u0440\u0430",
44
+ "30": "\u041a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0438",
45
+ "31": "\u0417\u0430\u043c\u0435\u0447\u0430\u043d\u0438\u044f \u043f\u043e \u0440\u0430\u0431\u043e\u0442\u0435 \u0441\u0431\u043e\u0440\u0449\u0438\u043a\u0430",
46
+ "32": "\u041e\u0442\u043c\u0435\u043d\u0438\u043b\u0438 \u0437\u0430\u043a\u0430\u0437",
47
+ "33": "\u0417\u043d\u0430\u043d\u0438\u0435 \u0440\u0443\u0441\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430",
48
+ "34": "\u041f\u0440\u0438\u0432\u0435\u0437\u043b\u0438 \u0447\u0443\u0436\u043e\u0439 \u0437\u0430\u043a\u0430\u0437",
49
+ "35": "\u0414\u043e\u043b\u0433\u043e \u043d\u0430 \u0441\u0431\u043e\u0440\u043a\u0435",
50
+ "36": "\u0421\u0440\u0430\u0432\u043d\u0438\u0432\u0430\u044e\u0442 \u0441 \u043a\u043e\u043d\u043a\u0443\u0440\u0435\u043d\u0442\u0430\u043c\u0438",
51
+ "37": "\u0421\u043a\u0438\u0434\u043a\u0438 \u0437\u0430 \u043e\u043f\u043e\u0437\u0434\u0430\u043d\u0438\u0435",
52
+ "38": "\u041a\u0443\u0440\u044c\u0435\u0440\u044b \u043e\u0442\u043c\u0435\u043d\u044f\u044e\u0442 \u0437\u0430\u043a\u0430\u0437",
53
+ "39": "\u041d\u0435 \u0442\u044f\u043d\u0435\u0442 \u043d\u0430 \u0442\u0435\u043d\u0434\u0435\u043d\u0446\u0438\u044e",
54
+ "40": "\u0418\u0441\u043f\u043e\u0440\u0447\u0435\u043d\u043d\u044b\u0435 \u0442\u043e\u0432\u0430\u0440\u044b",
55
+ "41": "\u041d\u0435 \u043d\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0438\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f",
56
+ "42": "\u041f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0435 \u0437\u0430\u0432\u0438\u0441\u0430\u0435\u0442",
57
+ "43": "\u0411\u044b\u0441\u0442\u0440\u0430\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0430",
58
+ "44": "\u0423\u0441\u043b\u043e\u0432\u0438\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u043a\u0443\u0440\u044c\u0435\u0440\u043e\u0432",
59
+ "45": "\u0421\u0431\u0435\u0440\u0421\u043f\u0430\u0441\u0438\u0431\u043e",
60
+ "46": "\u0412\u0440\u0435\u043c\u044f \u0440\u0430\u0431\u043e\u0442\u044b",
61
+ "47": "\u041d\u0435\u0443\u0434\u043e\u0431\u043d\u044b\u0439 \u043f\u043e\u0438\u0441\u043a",
62
+ "48": "\u041f\u043b\u0430\u0442\u0435\u0436\u0438",
63
+ "49": "\u0412\u043e\u0437\u0432\u0440\u0430\u0442 \u0434\u0435\u043d\u0435\u0433"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 4096,
67
+ "label2id": {
68
+ "\u0411\u043e\u043b\u044c\u0448\u0435 \u0430\u043a\u0446\u0438\u0439/\u0441\u043a\u0438\u0434\u043e\u043a": 23,
69
+ "\u0411\u044b\u0441\u0442\u0440\u0430\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0430": 43,
70
+ "\u0412\u043e\u0437\u0432\u0440\u0430\u0442 \u0434\u0435\u043d\u0435\u0433": 49,
71
+ "\u0412\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438 \u043d\u0435 \u0441\u043e\u043e\u0442\u0432\u0435\u0442\u0441\u0442\u0432\u0443\u0435\u0442 \u0437\u0430\u044f\u0432\u043b\u0435\u043d\u043e\u043c\u0443": 2,
72
+ "\u0412\u0440\u0435\u043c\u044f \u0440\u0430\u0431\u043e\u0442\u044b": 46,
73
+ "\u0412\u0441\u0451 \u043d\u043e\u0440\u043c\u0430\u043b\u044c\u043d\u043e": 20,
74
+ "\u0412\u0441\u0451 \u043f\u043b\u043e\u0445\u043e": 21,
75
+ "\u0412\u044b\u0441\u043e\u043a\u0430\u044f \u043c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f \u0441\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430": 8,
76
+ "\u0412\u044b\u0441\u043e\u043a\u0438\u0435 \u0446\u0435\u043d\u044b": 12,
77
+ "\u0414\u043e\u043b\u0433\u0430\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0430": 0,
78
+ "\u0414\u043e\u043b\u0433\u043e \u043d\u0430 \u0441\u0431\u043e\u0440\u043a\u0435": 35,
79
+ "\u0414\u043e\u0441\u0442\u0430\u0432\u043a\u0430 \u0441\u0442\u0430\u043b\u0430 \u0434\u043e\u043b\u0433\u043e\u0439": 1,
80
+ "\u0417\u0430\u043c\u0435\u0447\u0430\u043d\u0438\u044f \u043f\u043e \u0440\u0430\u0431\u043e\u0442\u0435 \u043a\u0443\u0440\u044c\u0435\u0440\u043e\u0432": 16,
81
+ "\u0417\u0430\u043c\u0435\u0447\u0430\u043d\u0438\u044f \u043f\u043e \u0440\u0430\u0431\u043e\u0442\u0435 \u0441\u0431\u043e\u0440\u0449\u0438\u043a\u0430": 31,
82
+ "\u0417\u043d\u0430\u043d\u0438\u0435 \u0440\u0443\u0441\u0441\u043a\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430": 33,
83
+ "\u0418\u0441\u043f\u043e\u0440\u0447\u0435\u043d\u043d\u044b\u0435 \u0442\u043e\u0432\u0430\u0440\u044b": 40,
84
+ "\u041a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u043f\u043e\u0434\u0434\u0435\u0440\u0436\u043a\u0438": 30,
85
+ "\u041a\u0430\u0447\u0435\u0441\u0442\u0432\u043e \u0442\u043e\u0432\u0430\u0440\u043e\u0432": 27,
86
+ "\u041a\u0443\u0440\u044c\u0435\u0440 \u043d\u0430 \u043a\u0430\u0440\u0442\u0435": 5,
87
+ "\u041a\u0443\u0440\u044c\u0435\u0440\u044b \u043e\u0442\u043c\u0435\u043d\u044f\u044e\u0442 \u0437\u0430\u043a\u0430\u0437": 38,
88
+ "\u041c\u0430\u043b\u0435\u043d\u044c\u043a\u0438\u0439 \u0430\u0441\u0441\u043e\u0440\u0442\u0438\u043c\u0435\u043d\u0442": 28,
89
+ "\u041c\u0438\u043d\u0438\u043c\u0430\u043b\u044c\u043d\u0430\u044f \u0441\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430": 10,
90
+ "\u041d\u0435 \u0434\u043e\u0432\u0435\u0437\u043b\u0438 \u0442\u043e\u0432\u0430\u0440": 13,
91
+ "\u041d\u0435 \u043d\u0440\u0430\u0432\u0438\u0442\u0441\u044f \u0438\u043d\u0442\u0435\u0440\u0444\u0435\u0439\u0441 \u043f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u044f": 41,
92
+ "\u041d\u0435 \u043e\u0442\u0441\u043b\u0435\u0434\u0438\u0442\u044c \u0440\u0435\u0430\u043b\u044c\u043d\u043e\u0435 \u0432\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438": 4,
93
+ "\u041d\u0435 \u043f\u0440\u0435\u0434\u0443\u043f\u0440\u0435\u0436\u0434\u0430\u0435\u043c \u043e\u0431 \u0443\u0434\u0430\u043b\u0435\u043d\u0438\u0438 \u0442\u043e\u0432\u0430\u0440\u0430": 7,
94
+ "\u041d\u0435 \u0441\u0440\u0430\u0431\u043e\u0442\u0430\u043b\u0430 \u0441\u043a\u0438\u0434\u043a\u0430/\u0430\u043a\u0446\u0438\u044f/\u043f\u0440\u043e\u043c\u043e\u043a\u043e\u0434": 26,
95
+ "\u041d\u0435 \u0442\u044f\u043d\u0435\u0442 \u043d\u0430 \u0442\u0435\u043d\u0434\u0435\u043d\u0446\u0438\u044e": 39,
96
+ "\u041d\u0435 \u0447\u0438\u0442\u0430\u0435\u043c \u043a\u043e\u043c\u043c\u0435\u043d\u0442\u0430\u0440\u0438\u0438": 17,
97
+ "\u041d\u0435\u043f\u043e\u043d\u044f\u0442\u043d\u043e \u043a\u0430\u043a \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u0441\u043a\u0438\u0434\u043a\u0430": 25,
98
+ "\u041d\u0435\u0442 \u0432 \u043d\u0430\u043b\u0438\u0447\u0438\u0438 \u0442\u043e\u0432\u0430\u0440\u0430": 29,
99
+ "\u041d\u0435\u0442 \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438 \u043f\u043e \u0430\u0434\u0440\u0435\u0441\u0443": 6,
100
+ "\u041d\u0435\u0442 \u0441\u043c\u044b\u0441\u043b\u0430": 19,
101
+ "\u041d\u0435\u0443\u0434\u043e\u0431\u043d\u044b\u0439 \u043f\u043e\u0438\u0441\u043a": 47,
102
+ "\u041e\u0442\u043c\u0435\u043d\u0438\u043b\u0438 \u0437\u0430\u043a\u0430\u0437": 32,
103
+ "\u041f\u043b\u0430\u0442\u0435\u0436\u0438": 48,
104
+ "\u041f\u0440\u0438\u0432\u0435\u0437\u043b\u0438 \u0447\u0443\u0436\u043e\u0439 \u0437\u0430\u043a\u0430\u0437": 34,
105
+ "\u041f\u0440\u0438\u043b\u043e\u0436\u0435\u043d\u0438\u0435 \u0437\u0430\u0432\u0438\u0441\u0430\u0435\u0442": 42,
106
+ "\u041f\u0440\u043e\u0441\u0440\u043e\u0447\u0435\u043d\u043d\u044b\u0435 \u0442\u043e\u0432\u0430\u0440\u044b": 15,
107
+ "\u0420\u0435\u0433\u0443\u043b\u044f\u0440\u043d\u044b\u0435 \u043e\u043f\u043e\u0437\u0434\u0430\u043d\u0438\u044f": 3,
108
+ "\u0421\u0431\u0435\u0440\u0421\u043f\u0430\u0441\u0438\u0431\u043e": 45,
109
+ "\u0421\u043a\u0438\u0434\u043a\u0430/\u043f\u0440\u043e\u043c\u043e\u043a\u043e\u0434 \u0440\u0430\u0441\u043f\u0440\u043e\u0441\u0442\u0440\u0430\u043d\u044f\u0435\u0442\u0441\u044f \u043d\u0435 \u043d\u0430 \u0432\u0441\u0435 \u0442\u043e\u0432\u0430\u0440\u044b": 24,
110
+ "\u0421\u043a\u0438\u0434\u043a\u0438 \u0434\u043b\u044f \u043f\u043e\u0441\u0442\u043e\u044f\u043d\u043d\u044b\u0445 \u043a\u043b\u0438\u0435\u043d\u0442\u043e\u0432": 22,
111
+ "\u0421\u043a\u0438\u0434\u043a\u0438 \u0437\u0430 \u043e\u043f\u043e\u0437\u0434\u0430\u043d\u0438\u0435": 37,
112
+ "\u0421\u043f\u0430\u0441\u0438\u0431\u043e": 18,
113
+ "\u0421\u0440\u0430\u0432\u043d\u0438\u0432\u0430\u044e\u0442 \u0441 \u043a\u043e\u043d\u043a\u0443\u0440\u0435\u043d\u0442\u0430\u043c\u0438": 36,
114
+ "\u0421\u0443\u043c\u043c\u0430 \u0437\u0430\u043a\u0430\u0437\u0430 \u043c\u0435\u043d\u044f\u0435\u0442\u0441\u044f \u0432\u043e \u0432\u0440\u0435\u043c\u044f \u043d\u0430\u0431\u043e\u0440\u0430 \u043a\u043e\u0440\u0437\u0438\u043d\u044b": 9,
115
+ "\u0422\u043e\u0432\u0430\u0440 \u0438\u0441\u043f\u043e\u0440\u0447\u0435\u043d \u0432\u043e \u0432\u0440\u0435\u043c\u044f \u0434\u043e\u0441\u0442\u0430\u0432\u043a\u0438": 14,
116
+ "\u0422\u043e\u0432\u0430\u0440\u044b \u0441 \u043f\u043e\u0434\u0445\u043e\u0434\u044f\u0449\u0438\u043c \u0441\u0440\u043e\u043a\u043e\u043c \u0433\u043e\u0434\u043d\u043e\u0441\u0442\u0438": 11,
117
+ "\u0423\u0441\u043b\u043e\u0432\u0438\u044f \u0440\u0430\u0431\u043e\u0442\u044b \u043a\u0443\u0440\u044c\u0435\u0440\u043e\u0432": 44
118
+ },
119
+ "layer_norm_eps": 1e-05,
120
+ "max_position_embeddings": 8194,
121
+ "model_type": "xlm-roberta",
122
+ "num_attention_heads": 16,
123
+ "num_hidden_layers": 24,
124
+ "output_past": true,
125
+ "pad_token_id": 1,
126
+ "position_embedding_type": "absolute",
127
+ "problem_type": "multi_label_classification",
128
+ "torch_dtype": "float32",
129
+ "transformers_version": "4.41.0",
130
+ "type_vocab_size": 1,
131
+ "use_cache": true,
132
+ "vocab_size": 46166
133
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38cc9d07cb0f9d195445899ca599846bfed471532f03ff449bb7bb2d3e94d883
3
+ size 1436359992
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1538f6a9b7588645542db5c84f16c0b8e00a93ba9dbef13792ea065bdda403fb
3
+ size 1042866
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "46165": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 512,
50
+ "model_max_length": 8192,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "sp_model_kwargs": {},
57
+ "stride": 0,
58
+ "tokenizer_class": "XLMRobertaTokenizer",
59
+ "truncation_side": "right",
60
+ "truncation_strategy": "longest_first",
61
+ "unk_token": "<unk>"
62
+ }