Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +28 -4
- tokenizer.json +2 -2
- tokenizer.model +3 -0
- tokenizer_config.json +14 -7
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 32000
|
3 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,6 +1,30 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
|
5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
}
|
tokenizer.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:249eebbb92b47ed3a5ceb2146c80e575c9d39b482ea22517337cf280d27e9c1a
|
3 |
+
size 1795484
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
-
"
|
|
|
3 |
"added_tokens_decoder": {
|
4 |
"0": {
|
5 |
"content": "<unk>",
|
@@ -25,8 +26,8 @@
|
|
25 |
"single_word": false,
|
26 |
"special": true
|
27 |
},
|
28 |
-
"
|
29 |
-
"content": "
|
30 |
"lstrip": false,
|
31 |
"normalized": false,
|
32 |
"rstrip": false,
|
@@ -34,11 +35,17 @@
|
|
34 |
"special": true
|
35 |
}
|
36 |
},
|
|
|
37 |
"bos_token": "<s>",
|
38 |
"clean_up_tokenization_spaces": false,
|
39 |
"eos_token": "</s>",
|
40 |
-
"
|
41 |
-
"
|
42 |
-
"
|
43 |
-
"
|
|
|
|
|
|
|
|
|
|
|
44 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[PAD]",
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
|
|
35 |
"special": true
|
36 |
}
|
37 |
},
|
38 |
+
"additional_special_tokens": [],
|
39 |
"bos_token": "<s>",
|
40 |
"clean_up_tokenization_spaces": false,
|
41 |
"eos_token": "</s>",
|
42 |
+
"legacy": true,
|
43 |
+
"model_max_length": 1024,
|
44 |
+
"pad_token": "[PAD]",
|
45 |
+
"padding_side": "right",
|
46 |
+
"sp_model_kwargs": {},
|
47 |
+
"spaces_between_special_tokens": false,
|
48 |
+
"tokenizer_class": "LlamaTokenizer",
|
49 |
+
"unk_token": "<unk>",
|
50 |
+
"use_default_system_prompt": true
|
51 |
}
|