hrishikeshpai30
commited on
Commit
•
a284765
1
Parent(s):
d7072bf
Upload tokenizer
Browse files- tokenizer_config.json +1 -1
- vocab.json +28 -28
tokenizer_config.json
CHANGED
@@ -3,7 +3,7 @@
|
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
-
"name_or_path": "/tmp/
|
7 |
"pad_token": "<pad>",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
|
|
3 |
"do_lower_case": false,
|
4 |
"eos_token": "</s>",
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"name_or_path": "/tmp/tmpbweimwo3",
|
7 |
"pad_token": "<pad>",
|
8 |
"replace_word_delimiter_char": " ",
|
9 |
"special_tokens_map_file": null,
|
vocab.json
CHANGED
@@ -1,34 +1,34 @@
|
|
1 |
{
|
2 |
-
"'":
|
3 |
"</s>": 2,
|
4 |
"<pad>": 0,
|
5 |
"<s>": 1,
|
6 |
"<unk>": 3,
|
7 |
-
"A":
|
8 |
-
"B":
|
9 |
-
"C":
|
10 |
-
"D":
|
11 |
-
"E":
|
12 |
-
"F":
|
13 |
-
"G":
|
14 |
-
"H":
|
15 |
-
"I":
|
16 |
-
"J":
|
17 |
-
"K":
|
18 |
-
"L":
|
19 |
-
"M":
|
20 |
-
"N":
|
21 |
-
"O":
|
22 |
-
"P":
|
23 |
-
"Q":
|
24 |
-
"R":
|
25 |
-
"S":
|
26 |
-
"T":
|
27 |
-
"U":
|
28 |
-
"V":
|
29 |
-
"W":
|
30 |
-
"X":
|
31 |
-
"Y":
|
32 |
-
"Z":
|
33 |
-
"|":
|
34 |
}
|
|
|
1 |
{
|
2 |
+
"'": 8,
|
3 |
"</s>": 2,
|
4 |
"<pad>": 0,
|
5 |
"<s>": 1,
|
6 |
"<unk>": 3,
|
7 |
+
"A": 22,
|
8 |
+
"B": 6,
|
9 |
+
"C": 17,
|
10 |
+
"D": 18,
|
11 |
+
"E": 26,
|
12 |
+
"F": 9,
|
13 |
+
"G": 24,
|
14 |
+
"H": 28,
|
15 |
+
"I": 27,
|
16 |
+
"J": 21,
|
17 |
+
"K": 31,
|
18 |
+
"L": 11,
|
19 |
+
"M": 15,
|
20 |
+
"N": 13,
|
21 |
+
"O": 10,
|
22 |
+
"P": 12,
|
23 |
+
"Q": 19,
|
24 |
+
"R": 23,
|
25 |
+
"S": 16,
|
26 |
+
"T": 20,
|
27 |
+
"U": 14,
|
28 |
+
"V": 7,
|
29 |
+
"W": 25,
|
30 |
+
"X": 4,
|
31 |
+
"Y": 29,
|
32 |
+
"Z": 5,
|
33 |
+
"|": 30
|
34 |
}
|