Dave17 commited on
Commit
dde0535
1 Parent(s): e64e39f

Upload 17 files

Browse files
.gitattributes ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ *.bin.* filter=lfs diff=lfs merge=lfs -text
2
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.h5 filter=lfs diff=lfs merge=lfs -text
5
+ *.tflite filter=lfs diff=lfs merge=lfs -text
6
+ *.tar.gz filter=lfs diff=lfs merge=lfs -text
7
+ *.ot filter=lfs diff=lfs merge=lfs -text
8
+ *.onnx filter=lfs diff=lfs merge=lfs -text
9
+ model.safetensors filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ license: apache-2.0
4
+ datasets:
5
+ - sst2
6
+ - glue
7
+ model-index:
8
+ - name: distilbert-base-uncased-finetuned-sst-2-english
9
+ results:
10
+ - task:
11
+ type: text-classification
12
+ name: Text Classification
13
+ dataset:
14
+ name: glue
15
+ type: glue
16
+ config: sst2
17
+ split: validation
18
+ metrics:
19
+ - type: accuracy
20
+ value: 0.9105504587155964
21
+ name: Accuracy
22
+ verified: true
23
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiN2YyOGMxYjY2Y2JhMjkxNjIzN2FmMjNiNmM2ZWViNGY3MTNmNWI2YzhiYjYxZTY0ZGUyN2M1NGIxZjRiMjQwZiIsInZlcnNpb24iOjF9.uui0srxV5ZHRhxbYN6082EZdwpnBgubPJ5R2-Wk8HTWqmxYE3QHidevR9LLAhidqGw6Ih93fK0goAXncld_gBg
24
+ - type: precision
25
+ value: 0.8978260869565218
26
+ name: Precision
27
+ verified: true
28
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMzgwYTYwYjA2MmM0ZTYwNDk0M2NmNTBkZmM2NGNhYzQ1OGEyN2NkNDQ3Mzc2NTQyMmZiNDJiNzBhNGVhZGUyOSIsInZlcnNpb24iOjF9.eHjLmw3K02OU69R2Au8eyuSqT3aBDHgZCn8jSzE3_urD6EUSSsLxUpiAYR4BGLD_U6-ZKcdxVo_A2rdXqvUJDA
29
+ - type: recall
30
+ value: 0.9301801801801802
31
+ name: Recall
32
+ verified: true
33
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGIzM2E3MTI2Mzc2MDYwNmU3ZTVjYmZmZDBkNjY4ZTc5MGY0Y2FkNDU3NjY1MmVkNmE3Y2QzMzAwZDZhOWY1NiIsInZlcnNpb24iOjF9.PUZlqmct13-rJWBXdHm5tdkXgETL9F82GNbbSR4hI8MB-v39KrK59cqzFC2Ac7kJe_DtOeUyosj34O_mFt_1DQ
34
+ - type: auc
35
+ value: 0.9716626673402374
36
+ name: AUC
37
+ verified: true
38
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMDM0YWIwZmQ4YjUwOGZmMWU2MjI1YjIxZGQ2MzNjMzRmZmYxMzZkNGFjODhlMDcyZDM1Y2RkMWZlOWQ0MWYwNSIsInZlcnNpb24iOjF9.E7GRlAXmmpEkTHlXheVkuL1W4WNjv4JO3qY_WCVsTVKiO7bUu0UVjPIyQ6g-J1OxsfqZmW3Leli1wY8vPBNNCQ
39
+ - type: f1
40
+ value: 0.9137168141592922
41
+ name: F1
42
+ verified: true
43
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMGU4MjNmOGYwZjZjMDQ1ZTkyZTA4YTc1MWYwOTM0NDM4ZWY1ZGVkNDY5MzNhYTQyZGFlNzIyZmUwMDg3NDU0NyIsInZlcnNpb24iOjF9.mW5ftkq50Se58M-jm6a2Pu93QeKa3MfV7xcBwvG3PSB_KNJxZWTCpfMQp-Cmx_EMlmI2siKOyd8akYjJUrzJCA
44
+ - type: loss
45
+ value: 0.39013850688934326
46
+ name: loss
47
+ verified: true
48
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMTZiNzAyZDc0MzUzMmE1MGJiN2JlYzFiODE5ZTNlNGE4MmI4YzRiMTc2ODEzMTUwZmEzOTgxNzc4YjJjZTRmNiIsInZlcnNpb24iOjF9.VqIC7uYC-ZZ8ss9zQOlRV39YVOOLc5R36sIzCcVz8lolh61ux_5djm2XjpP6ARc6KqEnXC4ZtfNXsX2HZfrtCQ
49
+ - task:
50
+ type: text-classification
51
+ name: Text Classification
52
+ dataset:
53
+ name: sst2
54
+ type: sst2
55
+ config: default
56
+ split: train
57
+ metrics:
58
+ - type: accuracy
59
+ value: 0.9885521685548412
60
+ name: Accuracy
61
+ verified: true
62
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiY2I3NzU3YzhmMDkxZTViY2M3OTY1NmI0ZTdmMDQxNjNjYzJiZmQxNzczM2E4YmExYTY5ODY0NDBkY2I4ZjNkOCIsInZlcnNpb24iOjF9.4Gtk3FeVc9sPWSqZIaeUXJ9oVlPzm-NmujnWpK2y5s1Vhp1l6Y1pK5_78wW0-NxSvQqV6qd5KQf_OAEpVAkQDA
63
+ - type: precision
64
+ value: 0.9881965062029833
65
+ name: Precision Macro
66
+ verified: true
67
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDdlZDMzY2I3MTAwYTljNmM4MGMyMzU2YjAzZDg1NDYwN2ZmM2Y5OWZhMjUyMGJiNjY1YmZiMzFhMDI2ODFhNyIsInZlcnNpb24iOjF9.cqmv6yBxu4St2mykRWrZ07tDsiSLdtLTz2hbqQ7Gm1rMzq9tdlkZ8MyJRxtME_Y8UaOG9rs68pV-gKVUs8wABw
68
+ - type: precision
69
+ value: 0.9885521685548412
70
+ name: Precision Micro
71
+ verified: true
72
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZjFlYzAzNmE1YjljNjUwNzBjZjEzZDY0ZDQyMmY5ZWM2OTBhNzNjYjYzYTk1YWE1NjU3YTMxZDQwOTE1Y2FkNyIsInZlcnNpb24iOjF9.jnCHOkUHuAOZZ_ZMVOnetx__OVJCS6LOno4caWECAmfrUaIPnPNV9iJ6izRO3sqkHRmxYpWBb-27GJ4N3LU-BQ
73
+ - type: precision
74
+ value: 0.9885639626373408
75
+ name: Precision Weighted
76
+ verified: true
77
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZGUyODFjNjBlNTE2MTY3ZDAxOGU1N2U0YjUyY2NiZjhkOGVmYThjYjBkNGU3NTRkYzkzNDQ2MmMwMjkwMWNiMyIsInZlcnNpb24iOjF9.zTNabMwApiZyXdr76QUn7WgGB7D7lP-iqS3bn35piqVTNsv3wnKjZOaKFVLIUvtBXq4gKw7N2oWxvWc4OcSNDg
78
+ - type: recall
79
+ value: 0.9886145346602994
80
+ name: Recall Macro
81
+ verified: true
82
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiNTU1YjlhODU3YTkyNTdiZDcwZGFlZDBiYjY0N2NjMGM2NTRiNjQ3MDNjNGMxOWY2ZGQ4NWU1YmMzY2UwZTI3YSIsInZlcnNpb24iOjF9.xaLPY7U-wHsJ3DDui1yyyM-xWjL0Jz5puRThy7fczal9x05eKEQ9s0a_WD-iLmapvJs0caXpV70hDe2NLcs-DA
83
+ - type: recall
84
+ value: 0.9885521685548412
85
+ name: Recall Micro
86
+ verified: true
87
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiODE0YTU0MDBlOGY4YzU0MjY5MzA3OTk2OGNhOGVkMmU5OGRjZmFiZWI2ZjY5ODEzZTQzMTI0N2NiOTVkNDliYiIsInZlcnNpb24iOjF9.SOt1baTBbuZRrsvGcak2sUwoTrQzmNCbyV2m1_yjGsU48SBH0NcKXicidNBSnJ6ihM5jf_Lv_B5_eOBkLfNWDQ
88
+ - type: recall
89
+ value: 0.9885521685548412
90
+ name: Recall Weighted
91
+ verified: true
92
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZWNkNmM0ZGRlNmYxYzIwNDk4OTI5MzIwZWU1NzZjZDVhMDcyNDFlMjBhNDQxODU5OWMwMWNhNGEzNjY3ZGUyOSIsInZlcnNpb24iOjF9.b15Fh70GwtlG3cSqPW-8VEZT2oy0CtgvgEOtWiYonOovjkIQ4RSLFVzVG-YfslaIyfg9RzMWzjhLnMY7Bpn2Aw
93
+ - type: f1
94
+ value: 0.9884019815052447
95
+ name: F1 Macro
96
+ verified: true
97
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiYmM4NjQ5Yjk5ODRhYTU1MTY3MmRhZDBmODM1NTg3OTFiNWM4NDRmYjI0MzZkNmQ1MzE3MzcxODZlYzBkYTMyYSIsInZlcnNpb24iOjF9.74RaDK8nBVuGRl2Se_-hwQvP6c4lvVxGHpcCWB4uZUCf2_HoC9NT9u7P3pMJfH_tK2cpV7U3VWGgSDhQDi-UBQ
98
+ - type: f1
99
+ value: 0.9885521685548412
100
+ name: F1 Micro
101
+ verified: true
102
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZDRmYWRmMmQ0YjViZmQxMzhhYTUyOTE1MTc0ZDU1ZjQyZjFhMDYzYzMzZDE0NzZlYzQyOTBhMTBhNmM5NTlkMiIsInZlcnNpb24iOjF9.VMn_psdAHIZTlW6GbjERZDe8MHhwzJ0rbjV_VJyuMrsdOh5QDmko-wEvaBWNEdT0cEKsbggm-6jd3Gh81PfHAQ
103
+ - type: f1
104
+ value: 0.9885546181087554
105
+ name: F1 Weighted
106
+ verified: true
107
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiMjUyZWFhZDZhMGQ3MzBmYmRiNDVmN2FkZDBjMjk3ODk0OTAxNGZkMWE0NzU5ZjI0NzE0NGZiNzM0N2Y2NDYyOSIsInZlcnNpb24iOjF9.YsXBhnzEEFEW6jw3mQlFUuIrW7Gabad2Ils-iunYJr-myg0heF8NEnEWABKFE1SnvCWt-69jkLza6SupeyLVCA
108
+ - type: loss
109
+ value: 0.040652573108673096
110
+ name: loss
111
+ verified: true
112
+ verifyToken: eyJhbGciOiJFZERTQSIsInR5cCI6IkpXVCJ9.eyJoYXNoIjoiZTc3YjU3MjdjMzkxODA5MjU5NGUyY2NkMGVhZDg3ZWEzMmU1YWVjMmI0NmU2OWEyZTkzMTVjNDZiYTc0YjIyNCIsInZlcnNpb24iOjF9.lA90qXZVYiILHMFlr6t6H81Oe8a-4KmeX-vyCC1BDia2ofudegv6Vb46-4RzmbtuKeV6yy6YNNXxXxqVak1pAg
113
+ ---
114
+
115
+ # DistilBERT base uncased finetuned SST-2
116
+
117
+ ## Table of Contents
118
+ - [Model Details](#model-details)
119
+ - [How to Get Started With the Model](#how-to-get-started-with-the-model)
120
+ - [Uses](#uses)
121
+ - [Risks, Limitations and Biases](#risks-limitations-and-biases)
122
+ - [Training](#training)
123
+
124
+ ## Model Details
125
+ **Model Description:** This model is a fine-tune checkpoint of [DistilBERT-base-uncased](https://huggingface.co/distilbert-base-uncased), fine-tuned on SST-2.
126
+ This model reaches an accuracy of 91.3 on the dev set (for comparison, Bert bert-base-uncased version reaches an accuracy of 92.7).
127
+ - **Developed by:** Hugging Face
128
+ - **Model Type:** Text Classification
129
+ - **Language(s):** English
130
+ - **License:** Apache-2.0
131
+ - **Parent Model:** For more details about DistilBERT, we encourage users to check out [this model card](https://huggingface.co/distilbert-base-uncased).
132
+ - **Resources for more information:**
133
+ - [Model Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/distilbert#transformers.DistilBertForSequenceClassification)
134
+ - [DistilBERT paper](https://arxiv.org/abs/1910.01108)
135
+
136
+ ## How to Get Started With the Model
137
+
138
+ Example of single-label classification:
139
+ ​​
140
+ ```python
141
+ import torch
142
+ from transformers import DistilBertTokenizer, DistilBertForSequenceClassification
143
+
144
+ tokenizer = DistilBertTokenizer.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
145
+ model = DistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased-finetuned-sst-2-english")
146
+
147
+ inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
148
+ with torch.no_grad():
149
+ logits = model(**inputs).logits
150
+
151
+ predicted_class_id = logits.argmax().item()
152
+ model.config.id2label[predicted_class_id]
153
+
154
+ ```
155
+
156
+ ## Uses
157
+
158
+ #### Direct Use
159
+
160
+ This model can be used for topic classification. You can use the raw model for either masked language modeling or next sentence prediction, but it's mostly intended to be fine-tuned on a downstream task. See the model hub to look for fine-tuned versions on a task that interests you.
161
+
162
+ #### Misuse and Out-of-scope Use
163
+ The model should not be used to intentionally create hostile or alienating environments for people. In addition, the model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
164
+
165
+
166
+ ## Risks, Limitations and Biases
167
+
168
+ Based on a few experimentations, we observed that this model could produce biased predictions that target underrepresented populations.
169
+
170
+ For instance, for sentences like `This film was filmed in COUNTRY`, this binary classification model will give radically different probabilities for the positive label depending on the country (0.89 if the country is France, but 0.08 if the country is Afghanistan) when nothing in the input indicates such a strong semantic shift. In this [colab](https://colab.research.google.com/gist/ageron/fb2f64fb145b4bc7c49efc97e5f114d3/biasmap.ipynb), [Aurélien Géron](https://twitter.com/aureliengeron) made an interesting map plotting these probabilities for each country.
171
+
172
+ <img src="https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english/resolve/main/map.jpeg" alt="Map of positive probabilities per country." width="500"/>
173
+
174
+ We strongly advise users to thoroughly probe these aspects on their use-cases in order to evaluate the risks of this model. We recommend looking at the following bias evaluation datasets as a place to start: [WinoBias](https://huggingface.co/datasets/wino_bias), [WinoGender](https://huggingface.co/datasets/super_glue), [Stereoset](https://huggingface.co/datasets/stereoset).
175
+
176
+
177
+
178
+ # Training
179
+
180
+
181
+ #### Training Data
182
+
183
+
184
+ The authors use the following Stanford Sentiment Treebank([sst2](https://huggingface.co/datasets/sst2)) corpora for the model.
185
+
186
+ #### Training Procedure
187
+
188
+ ###### Fine-tuning hyper-parameters
189
+
190
+
191
+ - learning_rate = 1e-5
192
+ - batch_size = 32
193
+ - warmup = 600
194
+ - max_seq_length = 128
195
+ - num_train_epochs = 3.0
196
+
197
+
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation": "gelu",
3
+ "architectures": [
4
+ "DistilBertForSequenceClassification"
5
+ ],
6
+ "attention_dropout": 0.1,
7
+ "dim": 768,
8
+ "dropout": 0.1,
9
+ "finetuning_task": "sst-2",
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "max_position_embeddings": 512,
21
+ "model_type": "distilbert",
22
+ "n_heads": 12,
23
+ "n_layers": 6,
24
+ "output_past": true,
25
+ "pad_token_id": 0,
26
+ "qa_dropout": 0.1,
27
+ "seq_classif_dropout": 0.2,
28
+ "sinusoidal_pos_embds": false,
29
+ "tie_weights_": true,
30
+ "vocab_size": 30522
31
+ }
map.jpeg ADDED
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3919835e442510166d267fe7cbe847e0c51cd26d9ba07b89a57b952b49b8aa
3
+ size 267832558
onnx/added_tokens.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 101,
3
+ "[MASK]": 103,
4
+ "[PAD]": 0,
5
+ "[SEP]": 102,
6
+ "[UNK]": 100
7
+ }
onnx/config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "qa_dropout": 0.1,
28
+ "seq_classif_dropout": 0.2,
29
+ "sinusoidal_pos_embds": false,
30
+ "tie_weights_": true,
31
+ "transformers_version": "4.34.0",
32
+ "vocab_size": 30522
33
+ }
onnx/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:252cf7048af94a1599019fef35961b2bd3d6db13df0b0a4b032b92baeae31939
3
+ size 267955711
onnx/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
onnx/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
onnx/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "additional_special_tokens": [],
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_basic_tokenize": true,
48
+ "do_lower_case": true,
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "DistilBertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
onnx/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60554cbd7781b09d87f1ececbea8c064b94e49a7f03fd88e8775bfe6cc3d9f88
3
+ size 267844284
rust_model.ot ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9db97da21b97a5e6db1212ce6a810a0c5e22c99daefe3355bae2117f78a0abb9
3
+ size 267846324
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b44df675bb34ccd8e57c14292c811ac7358b7c8e37c7f212745f640cd6019ac8
3
+ size 267949840
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model_max_length": 512, "do_lower_case": true}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff