Kornraphop Kawintiranon
commited on
Commit
•
d11f235
1
Parent(s):
1d1ff6b
fifth 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 |
+
{"[@USER00]": 30522, "[@USER01]": 30523, "[@USER02]": 30524, "[@USER03]": 30525, "[@USER04]": 30526, "[@USER05]": 30527, "[@USER06]": 30528, "[@USER07]": 30529, "[@USER08]": 30530, "[@USER09]": 30531, "[@USER10]": 30532, "[@USER11]": 30533, "[@USER12]": 30534, "[@USER13]": 30535, "[@USER14]": 30536, "[@USER15]": 30537, "[@USER16]": 30538, "[@USER17]": 30539, "[@USER18]": 30540, "[@USER19]": 30541, "[@USER20]": 30542, "[@USER21]": 30543, "[@USER22]": 30544, "[@USER23]": 30545, "[@USER24]": 30546, "[@USER25]": 30547, "[@USER26]": 30548, "[@USER27]": 30549, "[@USER28]": 30550, "[@USER29]": 30551, "[@USER30]": 30552, "[@USER31]": 30553, "[@USER32]": 30554, "[@USER33]": 30555, "[@USER34]": 30556, "[@USER35]": 30557, "[@USER36]": 30558, "[@USER37]": 30559, "[@USER38]": 30560, "[@USER39]": 30561, "[@USER40]": 30562, "[@USER41]": 30563, "[@USER42]": 30564, "[@USER43]": 30565, "[@USER44]": 30566, "[@USER45]": 30567, "[@USER46]": 30568, "[@USER47]": 30569, "[@USER48]": 30570, "[@USER49]": 30571, "[@USER50]": 30572, "[@USER51]": 30573, "[@USER52]": 30574, "[@USER53]": 30575, "[@USER54]": 30576, "[@USER55]": 30577, "[@USER56]": 30578, "[@USER57]": 30579, "[@USER58]": 30580, "[@USER59]": 30581, "[@USER60]": 30582, "[@USER61]": 30583, "[@USER62]": 30584, "[@USER63]": 30585, "[@USER64]": 30586, "[@USER65]": 30587, "[@USER66]": 30588, "[@USER67]": 30589, "[@USER68]": 30590, "[@USER69]": 30591, "[@USER70]": 30592, "[@USER71]": 30593, "[@USER72]": 30594, "[@USER73]": 30595, "[@USER74]": 30596, "[@USER75]": 30597, "[@USER76]": 30598, "[@USER77]": 30599, "[@USER78]": 30600, "[@USER79]": 30601, "[@USER80]": 30602, "[@USER81]": 30603, "[@USER82]": 30604, "[@USER83]": 30605, "[@USER84]": 30606, "[@USER85]": 30607, "[@USER86]": 30608, "[@USER87]": 30609, "[@USER88]": 30610, "[@USER89]": 30611, "[@USER90]": 30612, "[@USER91]": 30613, "[@USER92]": 30614, "[@USER93]": 30615, "[@USER94]": 30616, "[@USER95]": 30617, "[@USER96]": 30618, "[@USER97]": 30619, "[@USER98]": 30620, "[@USER99]": 30621, "[URL00]": 30622, "[URL01]": 30623, "[URL02]": 30624, "[URL03]": 30625, "[URL04]": 30626, "[URL05]": 30627, "[URL06]": 30628, "[URL07]": 30629, "[URL08]": 30630, "[URL09]": 30631, "[URL10]": 30632, "[URL11]": 30633, "[URL12]": 30634, "[URL13]": 30635, "[URL14]": 30636, "[URL15]": 30637, "[URL16]": 30638, "[URL17]": 30639, "[URL18]": 30640, "[URL19]": 30641, "[URL20]": 30642, "[URL21]": 30643, "[URL22]": 30644, "[URL23]": 30645, "[URL24]": 30646, "[URL25]": 30647, "[URL26]": 30648, "[URL27]": 30649, "[URL28]": 30650, "[URL29]": 30651, "[URL30]": 30652, "[URL31]": 30653, "[URL32]": 30654, "[URL33]": 30655, "[URL34]": 30656, "[URL35]": 30657, "[URL36]": 30658, "[URL37]": 30659, "[URL38]": 30660, "[URL39]": 30661, "[URL40]": 30662, "[URL41]": 30663, "[URL42]": 30664, "[URL43]": 30665, "[URL44]": 30666, "[URL45]": 30667, "[URL46]": 30668, "[URL47]": 30669, "[URL48]": 30670, "[URL49]": 30671, "[URL50]": 30672, "[URL51]": 30673, "[URL52]": 30674, "[URL53]": 30675, "[URL54]": 30676, "[URL55]": 30677, "[URL56]": 30678, "[URL57]": 30679, "[URL58]": 30680, "[URL59]": 30681, "[URL60]": 30682, "[URL61]": 30683, "[URL62]": 30684, "[URL63]": 30685, "[URL64]": 30686, "[URL65]": 30687, "[URL66]": 30688, "[URL67]": 30689, "[URL68]": 30690, "[URL69]": 30691, "[URL70]": 30692, "[URL71]": 30693, "[URL72]": 30694, "[URL73]": 30695, "[URL74]": 30696, "[URL75]": 30697, "[URL76]": 30698, "[URL77]": 30699, "[URL78]": 30700, "[URL79]": 30701, "[URL80]": 30702, "[URL81]": 30703, "[URL82]": 30704, "[URL83]": 30705, "[URL84]": 30706, "[URL85]": 30707, "[URL86]": 30708, "[URL87]": 30709, "[URL88]": 30710, "[URL89]": 30711, "[URL90]": 30712, "[URL91]": 30713, "[URL92]": 30714, "[URL93]": 30715, "[URL94]": 30716, "[URL95]": 30717, "[URL96]": 30718, "[URL97]": 30719, "[URL98]": 30720, "[URL99]": 30721}
|
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": 30722
|
30 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a613725ec5ed2d08f0dd436f918849e8c0d51c276bb0030453ec6e3056a54cb
|
3 |
+
size 438607153
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "additional_special_tokens": ["[@USER00]", "[@USER01]", "[@USER02]", "[@USER03]", "[@USER04]", "[@USER05]", "[@USER06]", "[@USER07]", "[@USER08]", "[@USER09]", "[@USER10]", "[@USER11]", "[@USER12]", "[@USER13]", "[@USER14]", "[@USER15]", "[@USER16]", "[@USER17]", "[@USER18]", "[@USER19]", "[@USER20]", "[@USER21]", "[@USER22]", "[@USER23]", "[@USER24]", "[@USER25]", "[@USER26]", "[@USER27]", "[@USER28]", "[@USER29]", "[@USER30]", "[@USER31]", "[@USER32]", "[@USER33]", "[@USER34]", "[@USER35]", "[@USER36]", "[@USER37]", "[@USER38]", "[@USER39]", "[@USER40]", "[@USER41]", "[@USER42]", "[@USER43]", "[@USER44]", "[@USER45]", "[@USER46]", "[@USER47]", "[@USER48]", "[@USER49]", "[@USER50]", "[@USER51]", "[@USER52]", "[@USER53]", "[@USER54]", "[@USER55]", "[@USER56]", "[@USER57]", "[@USER58]", "[@USER59]", "[@USER60]", "[@USER61]", "[@USER62]", "[@USER63]", "[@USER64]", "[@USER65]", "[@USER66]", "[@USER67]", "[@USER68]", "[@USER69]", "[@USER70]", "[@USER71]", "[@USER72]", "[@USER73]", "[@USER74]", "[@USER75]", "[@USER76]", "[@USER77]", "[@USER78]", "[@USER79]", "[@USER80]", "[@USER81]", "[@USER82]", "[@USER83]", "[@USER84]", "[@USER85]", "[@USER86]", "[@USER87]", "[@USER88]", "[@USER89]", "[@USER90]", "[@USER91]", "[@USER92]", "[@USER93]", "[@USER94]", "[@USER95]", "[@USER96]", "[@USER97]", "[@USER98]", "[@USER99]", "[URL00]", "[URL01]", "[URL02]", "[URL03]", "[URL04]", "[URL05]", "[URL06]", "[URL07]", "[URL08]", "[URL09]", "[URL10]", "[URL11]", "[URL12]", "[URL13]", "[URL14]", "[URL15]", "[URL16]", "[URL17]", "[URL18]", "[URL19]", "[URL20]", "[URL21]", "[URL22]", "[URL23]", "[URL24]", "[URL25]", "[URL26]", "[URL27]", "[URL28]", "[URL29]", "[URL30]", "[URL31]", "[URL32]", "[URL33]", "[URL34]", "[URL35]", "[URL36]", "[URL37]", "[URL38]", "[URL39]", "[URL40]", "[URL41]", "[URL42]", "[URL43]", "[URL44]", "[URL45]", "[URL46]", "[URL47]", "[URL48]", "[URL49]", "[URL50]", "[URL51]", "[URL52]", "[URL53]", "[URL54]", "[URL55]", "[URL56]", "[URL57]", "[URL58]", "[URL59]", "[URL60]", "[URL61]", "[URL62]", "[URL63]", "[URL64]", "[URL65]", "[URL66]", "[URL67]", "[URL68]", "[URL69]", "[URL70]", "[URL71]", "[URL72]", "[URL73]", "[URL74]", "[URL75]", "[URL76]", "[URL77]", "[URL78]", "[URL79]", "[URL80]", "[URL81]", "[URL82]", "[URL83]", "[URL84]", "[URL85]", "[URL86]", "[URL87]", "[URL88]", "[URL89]", "[URL90]", "[URL91]", "[URL92]", "[URL93]", "[URL94]", "[URL95]", "[URL96]", "[URL97]", "[URL98]", "[URL99]"]}
|
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
|
|