ankur310794
commited on
Commit
•
4c58bd0
1
Parent(s):
09be205
Update from
Browse files- added_tokens.json +1 -0
- config.json +23 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"td_colspan": 30522, "th_colspan": 30523, "``": 30524, "''": 30525, "--": 30526, "<dd>": 30527, "<dl>": 30528, "<dt>": 30529, "<h1>": 30530, "<h2>": 30531, "<h3>": 30532, "<li>": 30533, "<ol>": 30534, "<p>": 30535, "<table>": 30536, "<td>": 30537, "<th>": 30538, "<tr>": 30539, "<ul>": 30540, "</dd>": 30541, "</dl>": 30542, "</dt>": 30543, "</h1>": 30544, "</h2>": 30545, "</h3>": 30546, "</li>": 30547, "</ol>": 30548, "</p>": 30549, "</table>": 30550, "</td>": 30551, "</th>": 30552, "</tr>": 30553, "</ul>": 30554}
|
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForMaskedLM"
|
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": 1024,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 4096,
|
12 |
+
"layer_norm_eps": 1e-12,
|
13 |
+
"max_position_embeddings": 512,
|
14 |
+
"model_type": "bert",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"position_embedding_type": "absolute",
|
19 |
+
"transformers_version": "4.4.2",
|
20 |
+
"type_vocab_size": 2,
|
21 |
+
"use_cache": true,
|
22 |
+
"vocab_size": 30555
|
23 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbfdaef353674f4ebaf791226d6d656417d5e67ab1947176c0034d14f342cb97
|
3 |
+
size 1341237512
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/475d46024228961ca8770cead39e1079f135fd2441d14cf216727ffac8d41d78.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "bert-large-uncased"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|