Upload tokenizer
Browse files- tokenizer.json +14 -14
- tokenizer_config.json +14 -14
tokenizer.json
CHANGED
|
@@ -27,17 +27,17 @@
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
-
"normalized":
|
| 31 |
-
"special":
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
"content": "<|assistant|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
-
"rstrip":
|
| 39 |
-
"normalized":
|
| 40 |
-
"special":
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
|
@@ -80,18 +80,18 @@
|
|
| 80 |
"content": "<|system|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
-
"rstrip":
|
| 84 |
-
"normalized":
|
| 85 |
-
"special":
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 9,
|
| 89 |
"content": "<|end|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
-
"rstrip":
|
| 93 |
-
"normalized":
|
| 94 |
-
"special":
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 10,
|
|
@@ -116,9 +116,9 @@
|
|
| 116 |
"content": "<|user|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
-
"rstrip":
|
| 120 |
-
"normalized":
|
| 121 |
-
"special":
|
| 122 |
}
|
| 123 |
],
|
| 124 |
"normalizer": {
|
|
|
|
| 27 |
"single_word": false,
|
| 28 |
"lstrip": false,
|
| 29 |
"rstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"special": false
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"id": 3,
|
| 35 |
"content": "<|assistant|>",
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"special": false
|
| 41 |
},
|
| 42 |
{
|
| 43 |
"id": 4,
|
|
|
|
| 80 |
"content": "<|system|>",
|
| 81 |
"single_word": false,
|
| 82 |
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": true,
|
| 85 |
+
"special": false
|
| 86 |
},
|
| 87 |
{
|
| 88 |
"id": 9,
|
| 89 |
"content": "<|end|>",
|
| 90 |
"single_word": false,
|
| 91 |
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": true,
|
| 94 |
+
"special": false
|
| 95 |
},
|
| 96 |
{
|
| 97 |
"id": 10,
|
|
|
|
| 116 |
"content": "<|user|>",
|
| 117 |
"single_word": false,
|
| 118 |
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": true,
|
| 121 |
+
"special": false
|
| 122 |
}
|
| 123 |
],
|
| 124 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -21,18 +21,18 @@
|
|
| 21 |
"2": {
|
| 22 |
"content": "<|endoftext|>",
|
| 23 |
"lstrip": false,
|
| 24 |
-
"normalized":
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
-
"special":
|
| 28 |
},
|
| 29 |
"3": {
|
| 30 |
"content": "<|assistant|>",
|
| 31 |
"lstrip": false,
|
| 32 |
-
"normalized":
|
| 33 |
-
"rstrip":
|
| 34 |
"single_word": false,
|
| 35 |
-
"special":
|
| 36 |
},
|
| 37 |
"4": {
|
| 38 |
"content": "<|placeholder1|>",
|
|
@@ -69,18 +69,18 @@
|
|
| 69 |
"8": {
|
| 70 |
"content": "<|system|>",
|
| 71 |
"lstrip": false,
|
| 72 |
-
"normalized":
|
| 73 |
-
"rstrip":
|
| 74 |
"single_word": false,
|
| 75 |
-
"special":
|
| 76 |
},
|
| 77 |
"9": {
|
| 78 |
"content": "<|end|>",
|
| 79 |
"lstrip": false,
|
| 80 |
-
"normalized":
|
| 81 |
-
"rstrip":
|
| 82 |
"single_word": false,
|
| 83 |
-
"special":
|
| 84 |
},
|
| 85 |
"10": {
|
| 86 |
"content": "<|placeholder5|>",
|
|
@@ -101,10 +101,10 @@
|
|
| 101 |
"12": {
|
| 102 |
"content": "<|user|>",
|
| 103 |
"lstrip": false,
|
| 104 |
-
"normalized":
|
| 105 |
-
"rstrip":
|
| 106 |
"single_word": false,
|
| 107 |
-
"special":
|
| 108 |
}
|
| 109 |
},
|
| 110 |
"bos_token": "<s>",
|
|
|
|
| 21 |
"2": {
|
| 22 |
"content": "<|endoftext|>",
|
| 23 |
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
+
"special": false
|
| 28 |
},
|
| 29 |
"3": {
|
| 30 |
"content": "<|assistant|>",
|
| 31 |
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
"single_word": false,
|
| 35 |
+
"special": false
|
| 36 |
},
|
| 37 |
"4": {
|
| 38 |
"content": "<|placeholder1|>",
|
|
|
|
| 69 |
"8": {
|
| 70 |
"content": "<|system|>",
|
| 71 |
"lstrip": false,
|
| 72 |
+
"normalized": true,
|
| 73 |
+
"rstrip": false,
|
| 74 |
"single_word": false,
|
| 75 |
+
"special": false
|
| 76 |
},
|
| 77 |
"9": {
|
| 78 |
"content": "<|end|>",
|
| 79 |
"lstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"rstrip": false,
|
| 82 |
"single_word": false,
|
| 83 |
+
"special": false
|
| 84 |
},
|
| 85 |
"10": {
|
| 86 |
"content": "<|placeholder5|>",
|
|
|
|
| 101 |
"12": {
|
| 102 |
"content": "<|user|>",
|
| 103 |
"lstrip": false,
|
| 104 |
+
"normalized": true,
|
| 105 |
+
"rstrip": false,
|
| 106 |
"single_word": false,
|
| 107 |
+
"special": false
|
| 108 |
}
|
| 109 |
},
|
| 110 |
"bos_token": "<s>",
|