Upload tokenizer
Browse files- special_tokens_map.json +6 -1
- tokenizer_config.json +47 -7
special_tokens_map.json
CHANGED
@@ -1,4 +1,10 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
@@ -13,7 +19,6 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
"bos_token": {
|
9 |
"content": "<s>",
|
10 |
"lstrip": false,
|
|
|
19 |
"rstrip": false,
|
20 |
"single_word": false
|
21 |
},
|
|
|
22 |
"unk_token": {
|
23 |
"content": "<unk>",
|
24 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -26,18 +25,59 @@
|
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
-
"
|
|
|
|
|
|
|
35 |
"model_max_length": 1000000000000000019884624838656,
|
36 |
-
"pad_token":
|
|
|
37 |
"sp_model_kwargs": {},
|
38 |
-
"
|
39 |
-
"tokenizer_class": "
|
40 |
"unk_token": "<unk>",
|
41 |
-
"use_default_system_prompt": false
|
42 |
-
"use_fast": true
|
43 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
+
},
|
29 |
+
"32007": {
|
30 |
+
"content": "β<PRE>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32008": {
|
38 |
+
"content": "β<SUF>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32009": {
|
46 |
+
"content": "β<MID>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32010": {
|
54 |
+
"content": "β<EOT>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
}
|
61 |
},
|
62 |
+
"additional_special_tokens": [
|
63 |
+
"β<PRE>",
|
64 |
+
"β<MID>",
|
65 |
+
"β<SUF>",
|
66 |
+
"β<EOT>"
|
67 |
+
],
|
68 |
"bos_token": "<s>",
|
69 |
"clean_up_tokenization_spaces": false,
|
70 |
"eos_token": "</s>",
|
71 |
+
"eot_token": "β<EOT>",
|
72 |
+
"fill_token": "<FILL_ME>",
|
73 |
+
"legacy": null,
|
74 |
+
"middle_token": "β<MID>",
|
75 |
"model_max_length": 1000000000000000019884624838656,
|
76 |
+
"pad_token": null,
|
77 |
+
"prefix_token": "β<PRE>",
|
78 |
"sp_model_kwargs": {},
|
79 |
+
"suffix_token": "β<SUF>",
|
80 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
81 |
"unk_token": "<unk>",
|
82 |
+
"use_default_system_prompt": false
|
|
|
83 |
}
|