Kornraphop Kawintiranon
commited on
Commit
•
ffe14cb
1
Parent(s):
30782ff
second version
Browse files- added_tokens.json +1 -0
- config.json +30 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"#trumptrain": 30522, "#trump2020landslide": 30523, "#voteblue2020": 30524, "#bidenharris2020": 30525, "#maga": 30526, "#biden2020": 30527, "#votebluetosaveamerica": 30528, "#demdebate": 30529, "#votebidenharris2020": 30530, "#democraticdebate": 30531, "#wwg1wga": 30532, "#voteblue": 30533, "#maga2020": 30534, "gop": 30535, "#demconvention": 30536, "#trump2020": 30537, "#kag": 30538, "#kag2020": 30539, "@gop": 30540, "#votebluetoendthisnightmare": 30541}
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"gradient_checkpointing": false,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"LABEL_0": 0,
|
19 |
+
"LABEL_1": 1,
|
20 |
+
"LABEL_2": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-12,
|
23 |
+
"max_position_embeddings": 512,
|
24 |
+
"model_type": "bert",
|
25 |
+
"num_attention_heads": 12,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"pad_token_id": 0,
|
28 |
+
"type_vocab_size": 2,
|
29 |
+
"vocab_size": 30542
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af88bbd61fc0ba0c73f52daa8c9ea453c0ad2a755d2ad23c4c7747ebd9c46438
|
3 |
+
size 438054193
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "model_max_length": 512, "special_tokens_map_file": "/home/ken/projects/Stance-Sentiment/language_models/English/election2020/bert-election2020-tweet-5M-censored-only-url-1ep-lr-1e-4/special_tokens_map.json", "full_tokenizer_file": null}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|