Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +3 -21
- tokenizer.json +8 -8
- tokenizer_config.json +61 -24
added_tokens.json
CHANGED
@@ -1,4 +1,7 @@
|
|
1 |
{
|
|
|
|
|
|
|
2 |
"β<EOT>": 32003,
|
3 |
"β<MID>": 32001,
|
4 |
"β<PRE>": 32000,
|
|
|
1 |
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0,
|
5 |
"β<EOT>": 32003,
|
6 |
"β<MID>": 32001,
|
7 |
"β<PRE>": 32000,
|
special_tokens_map.json
CHANGED
@@ -5,25 +5,7 @@
|
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
-
"bos_token":
|
9 |
-
|
10 |
-
|
11 |
-
"normalized": true,
|
12 |
-
"rstrip": false,
|
13 |
-
"single_word": false
|
14 |
-
},
|
15 |
-
"eos_token": {
|
16 |
-
"content": "</s>",
|
17 |
-
"lstrip": false,
|
18 |
-
"normalized": true,
|
19 |
-
"rstrip": false,
|
20 |
-
"single_word": false
|
21 |
-
},
|
22 |
-
"unk_token": {
|
23 |
-
"content": "<unk>",
|
24 |
-
"lstrip": false,
|
25 |
-
"normalized": true,
|
26 |
-
"rstrip": false,
|
27 |
-
"single_word": false
|
28 |
-
}
|
29 |
}
|
|
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
+
"bos_token": "<s>",
|
9 |
+
"eos_token": "</s>",
|
10 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
tokenizer.json
CHANGED
@@ -34,8 +34,8 @@
|
|
34 |
"id": 32000,
|
35 |
"content": "β<PRE>",
|
36 |
"single_word": false,
|
37 |
-
"lstrip":
|
38 |
-
"rstrip":
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
@@ -43,8 +43,8 @@
|
|
43 |
"id": 32001,
|
44 |
"content": "β<MID>",
|
45 |
"single_word": false,
|
46 |
-
"lstrip":
|
47 |
-
"rstrip":
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
},
|
@@ -52,8 +52,8 @@
|
|
52 |
"id": 32002,
|
53 |
"content": "β<SUF>",
|
54 |
"single_word": false,
|
55 |
-
"lstrip":
|
56 |
-
"rstrip":
|
57 |
"normalized": false,
|
58 |
"special": true
|
59 |
},
|
@@ -61,8 +61,8 @@
|
|
61 |
"id": 32003,
|
62 |
"content": "β<EOT>",
|
63 |
"single_word": false,
|
64 |
-
"lstrip":
|
65 |
-
"rstrip":
|
66 |
"normalized": false,
|
67 |
"special": true
|
68 |
}
|
|
|
34 |
"id": 32000,
|
35 |
"content": "β<PRE>",
|
36 |
"single_word": false,
|
37 |
+
"lstrip": true,
|
38 |
+
"rstrip": true,
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
},
|
|
|
43 |
"id": 32001,
|
44 |
"content": "β<MID>",
|
45 |
"single_word": false,
|
46 |
+
"lstrip": true,
|
47 |
+
"rstrip": true,
|
48 |
"normalized": false,
|
49 |
"special": true
|
50 |
},
|
|
|
52 |
"id": 32002,
|
53 |
"content": "β<SUF>",
|
54 |
"single_word": false,
|
55 |
+
"lstrip": true,
|
56 |
+
"rstrip": true,
|
57 |
"normalized": false,
|
58 |
"special": true
|
59 |
},
|
|
|
61 |
"id": 32003,
|
62 |
"content": "β<EOT>",
|
63 |
"single_word": false,
|
64 |
+
"lstrip": true,
|
65 |
+
"rstrip": true,
|
66 |
"normalized": false,
|
67 |
"special": true
|
68 |
}
|
tokenizer_config.json
CHANGED
@@ -1,27 +1,71 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"additional_special_tokens": [
|
3 |
"β<PRE>",
|
4 |
"β<MID>",
|
5 |
"β<SUF>",
|
6 |
"β<EOT>"
|
7 |
],
|
8 |
-
"bos_token":
|
9 |
-
"__type": "AddedToken",
|
10 |
-
"content": "<s>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": true,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"clean_up_tokenization_spaces": false,
|
17 |
-
"eos_token":
|
18 |
-
"__type": "AddedToken",
|
19 |
-
"content": "</s>",
|
20 |
-
"lstrip": false,
|
21 |
-
"normalized": true,
|
22 |
-
"rstrip": false,
|
23 |
-
"single_word": false
|
24 |
-
},
|
25 |
"eot_token": "β<EOT>",
|
26 |
"fill_token": "<FILL_ME>",
|
27 |
"legacy": null,
|
@@ -32,13 +76,6 @@
|
|
32 |
"sp_model_kwargs": {},
|
33 |
"suffix_token": "β<SUF>",
|
34 |
"tokenizer_class": "CodeLlamaTokenizer",
|
35 |
-
"unk_token":
|
36 |
-
"__type": "AddedToken",
|
37 |
-
"content": "<unk>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false
|
42 |
-
},
|
43 |
"use_default_system_prompt": false
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": true,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "β<PRE>",
|
29 |
+
"lstrip": true,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": true,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "β<MID>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": true,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "β<SUF>",
|
45 |
+
"lstrip": true,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": true,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"32003": {
|
52 |
+
"content": "β<EOT>",
|
53 |
+
"lstrip": true,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": true,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
}
|
59 |
+
},
|
60 |
"additional_special_tokens": [
|
61 |
"β<PRE>",
|
62 |
"β<MID>",
|
63 |
"β<SUF>",
|
64 |
"β<EOT>"
|
65 |
],
|
66 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
"clean_up_tokenization_spaces": false,
|
68 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
69 |
"eot_token": "β<EOT>",
|
70 |
"fill_token": "<FILL_ME>",
|
71 |
"legacy": null,
|
|
|
76 |
"sp_model_kwargs": {},
|
77 |
"suffix_token": "β<SUF>",
|
78 |
"tokenizer_class": "CodeLlamaTokenizer",
|
79 |
+
"unk_token": "<unk>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
"use_default_system_prompt": false
|
81 |
}
|