Commit
•
7890584
1
Parent(s):
941c288
Upload tokenizer
Browse files- special_tokens_map.json +14 -0
- tokenizer.json +0 -0
- tokenizer_config.json +19 -1
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
{
|
| 4 |
"content": "<|im_end|>",
|
| 5 |
"lstrip": false,
|
|
@@ -20,6 +27,13 @@
|
|
| 20 |
"normalized": false,
|
| 21 |
"rstrip": false,
|
| 22 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"bos_token": {
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
{
|
| 11 |
"content": "<|im_end|>",
|
| 12 |
"lstrip": false,
|
|
|
|
| 27 |
"normalized": false,
|
| 28 |
"rstrip": false,
|
| 29 |
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<|System|>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
}
|
| 38 |
],
|
| 39 |
"bos_token": {
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,6 +43,22 @@
|
|
| 43 |
"single_word": false,
|
| 44 |
"special": true
|
| 45 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
"7": {
|
| 47 |
"content": "<|im_end|>",
|
| 48 |
"lstrip": false,
|
|
@@ -53,9 +69,11 @@
|
|
| 53 |
}
|
| 54 |
},
|
| 55 |
"additional_special_tokens": [
|
|
|
|
| 56 |
"<|im_end|>",
|
| 57 |
"<|Human|>",
|
| 58 |
-
"<|Assistant|>"
|
|
|
|
| 59 |
],
|
| 60 |
"bos_token": "<|startoftext|>",
|
| 61 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 43 |
"single_word": false,
|
| 44 |
"special": true
|
| 45 |
},
|
| 46 |
+
"5": {
|
| 47 |
+
"content": "<|System|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"6": {
|
| 55 |
+
"content": "<|im_start|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
"7": {
|
| 63 |
"content": "<|im_end|>",
|
| 64 |
"lstrip": false,
|
|
|
|
| 69 |
}
|
| 70 |
},
|
| 71 |
"additional_special_tokens": [
|
| 72 |
+
"<|im_start|>",
|
| 73 |
"<|im_end|>",
|
| 74 |
"<|Human|>",
|
| 75 |
+
"<|Assistant|>",
|
| 76 |
+
"<|System|>"
|
| 77 |
],
|
| 78 |
"bos_token": "<|startoftext|>",
|
| 79 |
"clean_up_tokenization_spaces": false,
|