ddevaul commited on
Commit
903427f
1 Parent(s): aa1309f

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -0
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ ---
4
+
5
+
6
+ ## How to use
7
+
8
+ Requirements:
9
+
10
+ ```bash
11
+ git clone https://github.com/ddevaul/transformers
12
+ ```
13
+
14
+ ```bash
15
+ cd transformers
16
+ ```
17
+
18
+ ```bash
19
+ pip install -r requirements.txt
20
+ ```
21
+
22
+ ```bash
23
+ cd ..
24
+ ```
25
+
26
+ Now open your file and add this:
27
+
28
+ ```python
29
+ import sys
30
+ import torch
31
+ sys.path.append('./transformers/src')
32
+ from torch.utils.checkpoint import checkpoint
33
+ from transformers2 import BertConfig, BertTokenizer
34
+ from transformers2.models.bert import BertForMaskedLM
35
+
36
+ preload_path = 'cabrooks/character-level-logion'
37
+ char_tokenizer = BertTokenizer.from_pretrained(preload_path)
38
+ wordpiece_tokenizer = BertTokenizer.from_pretrained("cabrooks/LOGION-50k_wordpiece")
39
+ config = BertConfig()
40
+ config.word_piece_vocab_size = 50000
41
+ config.vocab_size = char_tokenizer.vocab_size
42
+ config.char_tokenizer = char_tokenizer
43
+ config.wordpiece_tokenizer = wordpiece_tokenizer
44
+ config.max_position_embeddings = 1024
45
+ config.device2 = device
46
+ model = BertForMaskedLM(config).to(device)
47
+ ```
48
+
49
+
50
+ ## Cite
51
+
52
+ If you use this model in your research, please cite the paper:
53
+
54
+ ```
55
+ @misc{logion-base,
56
+ title={Logion: Machine Learning for Greek Philology},
57
+ author={Cowen-Breen, C. and Brooks, C. and Haubold, J. and Graziosi, B.},
58
+ year={2023},
59
+ eprint={2305.01099},
60
+ archivePrefix={arXiv},
61
+ primaryClass={cs.CL}
62
+ }
63
+ ```