Yehor commited on
Commit
52fb804
·
verified ·
1 Parent(s): 7592e95

Upload EuroBertForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +199 -0
  2. config.json +128 -0
  3. model.safetensors +3 -0
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 +1,128 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EuroBERT/EuroBERT-210m",
3
+ "architectures": [
4
+ "EuroBertForSequenceClassification"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "auto_map": {
9
+ "AutoConfig": "EuroBERT/EuroBERT-210m--configuration_eurobert.EuroBertConfig",
10
+ "AutoModel": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertModel",
11
+ "AutoModelForMaskedLM": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertForMaskedLM",
12
+ "AutoModelForPreTraining": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertPreTrainedModel",
13
+ "AutoModelForSequenceClassification": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertForSequenceClassification"
14
+ },
15
+ "bos_token": "<|begin_of_text|>",
16
+ "bos_token_id": 128000,
17
+ "clf_pooling": "late",
18
+ "eos_token": "<|end_of_text|>",
19
+ "eos_token_id": 128001,
20
+ "head_dim": 64,
21
+ "hidden_act": "silu",
22
+ "hidden_dropout": 0.0,
23
+ "hidden_size": 768,
24
+ "id2label": {
25
+ "0": "inshe",
26
+ "1": "ekologiya",
27
+ "2": "ziemielnie_pravo",
28
+ "3": "reklama",
29
+ "4": "bankivska_diialnist",
30
+ "5": "prava_spozhivachiv",
31
+ "6": "medicina",
32
+ "7": "spadkove_pravo",
33
+ "8": "immighratsiia_iemighratsiia",
34
+ "9": "intieliektualna_vlasnist",
35
+ "10": "gospodarskie_pravo",
36
+ "11": "pidpriemnicka_dialnist",
37
+ "12": "opodatkuvannia",
38
+ "13": "piensiiata_sotsialni_viplati",
39
+ "14": "viiskovie_pravo",
40
+ "15": "sudova_praktika",
41
+ "16": "kriminalnie_pravo",
42
+ "17": "gromadianski_pravovidnosini",
43
+ "18": "strakhuvannya",
44
+ "19": "pratsevlashtuvvannya",
45
+ "20": "sotsialnyj_zakhist",
46
+ "21": "vighotovliennia_produktsiyi_ta_nadannia_poslugh",
47
+ "22": "litsienzuvannia",
48
+ "23": "reyestraciya_likvidaciya_bankrutstvo",
49
+ "24": "doghovirni_vidnosini",
50
+ "25": "administrativnie_pravo",
51
+ "26": "nierukhomist",
52
+ "27": "prava_vnutrishno_pieriemishchienikh_osib",
53
+ "28": "investitsii",
54
+ "29": "notarialni_pytanniia",
55
+ "30": "avtovlasnykam",
56
+ "31": "zhitlovi_pravovidnosini",
57
+ "32": "dovircha_vlastnist",
58
+ "33": "dierzhavni_zakupivli",
59
+ "34": "simejne_pravo",
60
+ "35": "mytne_pravo",
61
+ "36": "mizhnarodni_pravovidnosini",
62
+ "37": "korporativnie_pravo",
63
+ "38": "tsivilne_pravo"
64
+ },
65
+ "initializer_range": 0.02,
66
+ "intermediate_size": 3072,
67
+ "label2id": {
68
+ "administrativnie_pravo": 25,
69
+ "avtovlasnykam": 30,
70
+ "bankivska_diialnist": 4,
71
+ "dierzhavni_zakupivli": 33,
72
+ "doghovirni_vidnosini": 24,
73
+ "dovircha_vlastnist": 32,
74
+ "ekologiya": 1,
75
+ "gospodarskie_pravo": 10,
76
+ "gromadianski_pravovidnosini": 17,
77
+ "immighratsiia_iemighratsiia": 8,
78
+ "inshe": 0,
79
+ "intieliektualna_vlasnist": 9,
80
+ "investitsii": 28,
81
+ "korporativnie_pravo": 37,
82
+ "kriminalnie_pravo": 16,
83
+ "litsienzuvannia": 22,
84
+ "medicina": 6,
85
+ "mizhnarodni_pravovidnosini": 36,
86
+ "mytne_pravo": 35,
87
+ "nierukhomist": 26,
88
+ "notarialni_pytanniia": 29,
89
+ "opodatkuvannia": 12,
90
+ "pidpriemnicka_dialnist": 11,
91
+ "piensiiata_sotsialni_viplati": 13,
92
+ "pratsevlashtuvvannya": 19,
93
+ "prava_spozhivachiv": 5,
94
+ "prava_vnutrishno_pieriemishchienikh_osib": 27,
95
+ "reklama": 3,
96
+ "reyestraciya_likvidaciya_bankrutstvo": 23,
97
+ "simejne_pravo": 34,
98
+ "sotsialnyj_zakhist": 20,
99
+ "spadkove_pravo": 7,
100
+ "strakhuvannya": 18,
101
+ "sudova_praktika": 15,
102
+ "tsivilne_pravo": 38,
103
+ "vighotovliennia_produktsiyi_ta_nadannia_poslugh": 21,
104
+ "viiskovie_pravo": 14,
105
+ "zhitlovi_pravovidnosini": 31,
106
+ "ziemielnie_pravo": 2
107
+ },
108
+ "mask_token": "<|mask|>",
109
+ "mask_token_id": 128002,
110
+ "max_position_embeddings": 8192,
111
+ "mlp_bias": false,
112
+ "model_type": "eurobert",
113
+ "num_attention_heads": 12,
114
+ "num_hidden_layers": 12,
115
+ "num_key_value_heads": 12,
116
+ "pad_token": "<|end_of_text|>",
117
+ "pad_token_id": 128001,
118
+ "pretraining_tp": 1,
119
+ "problem_type": "single_label_classification",
120
+ "rms_norm_eps": 1e-05,
121
+ "rope_scaling": null,
122
+ "rope_theta": 250000,
123
+ "tie_word_embeddings": false,
124
+ "torch_dtype": "float32",
125
+ "transformers_version": "4.49.0",
126
+ "use_cache": false,
127
+ "vocab_size": 128256
128
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720a0eead32391516263f8d6fca05d7fc31f2c1557b3376607471ed0aa87bedc
3
+ size 849558948