Upload 4 files
Browse files- tokenizer.json +9 -44
- tokenizer.model +2 -2
- tokenizer_config.json +5 -36
tokenizer.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
8 |
-
"content": "<
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
@@ -14,7 +14,7 @@
|
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
17 |
-
"content": "
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
@@ -22,49 +22,13 @@
|
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
25 |
-
"id":
|
26 |
-
"content": "
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 4,
|
35 |
-
"content": "[INST]",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": false,
|
38 |
-
"rstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"special": false
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"id": 5,
|
44 |
-
"content": "[/INST]",
|
45 |
-
"single_word": false,
|
46 |
-
"lstrip": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"normalized": true,
|
49 |
-
"special": false
|
50 |
-
},
|
51 |
-
{
|
52 |
-
"id": 6,
|
53 |
-
"content": "<<SYS>>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": true,
|
58 |
-
"special": false
|
59 |
-
},
|
60 |
-
{
|
61 |
-
"id": 7,
|
62 |
-
"content": "<</SYS>>",
|
63 |
-
"single_word": false,
|
64 |
-
"lstrip": false,
|
65 |
-
"rstrip": false,
|
66 |
-
"normalized": true,
|
67 |
-
"special": false
|
68 |
}
|
69 |
],
|
70 |
"normalizer": {
|
@@ -130,7 +94,7 @@
|
|
130 |
"<s>": {
|
131 |
"id": "<s>",
|
132 |
"ids": [
|
133 |
-
|
134 |
],
|
135 |
"tokens": [
|
136 |
"<s>"
|
@@ -171,9 +135,10 @@
|
|
171 |
"fuse_unk": true,
|
172 |
"byte_fallback": true,
|
173 |
"vocab": {
|
174 |
-
"<
|
175 |
-
"
|
176 |
-
"
|
|
|
177 |
"[INST]": 4,
|
178 |
"[/INST]": 5,
|
179 |
"<<SYS>>": 6,
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
8 |
+
"content": "<s>",
|
9 |
"single_word": false,
|
10 |
"lstrip": false,
|
11 |
"rstrip": false,
|
|
|
14 |
},
|
15 |
{
|
16 |
"id": 1,
|
17 |
+
"content": "</s>",
|
18 |
"single_word": false,
|
19 |
"lstrip": false,
|
20 |
"rstrip": false,
|
|
|
22 |
"special": true
|
23 |
},
|
24 |
{
|
25 |
+
"id": 2,
|
26 |
+
"content": "<unk>",
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
94 |
"<s>": {
|
95 |
"id": "<s>",
|
96 |
"ids": [
|
97 |
+
0
|
98 |
],
|
99 |
"tokens": [
|
100 |
"<s>"
|
|
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
137 |
"vocab": {
|
138 |
+
"<s>": 0,
|
139 |
+
"</s>": 1,
|
140 |
+
"<unk>": 2,
|
141 |
+
"<pad>": 3,
|
142 |
"[INST]": 4,
|
143 |
"[/INST]": 5,
|
144 |
"<<SYS>>": 6,
|
tokenizer.model
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 sha256:29d04049f54d79e18d6554117a2d41ef630239e608222b54d6434acbb41494b2
|
3 |
+
size 483425
|
tokenizer_config.json
CHANGED
@@ -1,9 +1,10 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
-
"content": "<
|
7 |
"lstrip": false,
|
8 |
"normalized": false,
|
9 |
"rstrip": false,
|
@@ -11,52 +12,20 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
"special": true
|
20 |
},
|
21 |
-
"
|
22 |
-
"content": "
|
23 |
"lstrip": false,
|
24 |
"normalized": false,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"4": {
|
30 |
-
"content": "[INST]",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": true,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": false
|
36 |
-
},
|
37 |
-
"5": {
|
38 |
-
"content": "[/INST]",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": true,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": false
|
44 |
-
},
|
45 |
-
"6": {
|
46 |
-
"content": "<<SYS>>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": true,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false,
|
51 |
-
"special": false
|
52 |
-
},
|
53 |
-
"7": {
|
54 |
-
"content": "<</SYS>>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": true,
|
57 |
-
"rstrip": false,
|
58 |
-
"single_word": false,
|
59 |
-
"special": false
|
60 |
}
|
61 |
},
|
62 |
"bos_token": "<s>",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
+
"content": "<s>",
|
8 |
"lstrip": false,
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
|
|
12 |
"special": true
|
13 |
},
|
14 |
"1": {
|
15 |
+
"content": "</s>",
|
16 |
"lstrip": false,
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
"special": true
|
21 |
},
|
22 |
+
"2": {
|
23 |
+
"content": "<unk>",
|
24 |
"lstrip": false,
|
25 |
"normalized": false,
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
}
|
30 |
},
|
31 |
"bos_token": "<s>",
|