Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +9 -0
- tokenizer_config.json +10 -1
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,13 @@
|
|
| 13 |
"normalized": false,
|
| 14 |
"rstrip": false,
|
| 15 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
}
|
| 17 |
],
|
| 18 |
"bos_token": {
|
|
|
|
| 13 |
"normalized": false,
|
| 14 |
"rstrip": false,
|
| 15 |
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<image>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
}
|
| 24 |
],
|
| 25 |
"bos_token": {
|
tokenizer.json
CHANGED
|
@@ -47,6 +47,15 @@
|
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 50 |
}
|
| 51 |
],
|
| 52 |
"normalizer": {
|
|
|
|
| 47 |
"rstrip": false,
|
| 48 |
"normalized": false,
|
| 49 |
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 32002,
|
| 53 |
+
"content": "<image>",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
}
|
| 60 |
],
|
| 61 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -42,11 +42,20 @@
|
|
| 42 |
"rstrip": false,
|
| 43 |
"single_word": false,
|
| 44 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
}
|
| 46 |
},
|
| 47 |
"additional_special_tokens": [
|
| 48 |
"<|Assistant|>",
|
| 49 |
-
"<|User|>"
|
|
|
|
| 50 |
],
|
| 51 |
"bos_token": "<s>",
|
| 52 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 42 |
"rstrip": false,
|
| 43 |
"single_word": false,
|
| 44 |
"special": true
|
| 45 |
+
},
|
| 46 |
+
"32002": {
|
| 47 |
+
"content": "<image>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
}
|
| 54 |
},
|
| 55 |
"additional_special_tokens": [
|
| 56 |
"<|Assistant|>",
|
| 57 |
+
"<|User|>",
|
| 58 |
+
"<image>"
|
| 59 |
],
|
| 60 |
"bos_token": "<s>",
|
| 61 |
"clean_up_tokenization_spaces": false,
|