danielhanchen
commited on
Commit
β’
3908334
1
Parent(s):
1133ba7
Upload tokenizer
Browse files- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +84 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": "<unk>",
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
3 |
+
size 500058
|
tokenizer_config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
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": 16384,
|
76 |
+
"pad_token": "<unk>",
|
77 |
+
"padding_side": "right",
|
78 |
+
"prefix_token": "β<PRE>",
|
79 |
+
"sp_model_kwargs": {},
|
80 |
+
"suffix_token": "β<SUF>",
|
81 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
82 |
+
"unk_token": "<unk>",
|
83 |
+
"use_default_system_prompt": false
|
84 |
+
}
|