Upload tokenizer
Browse files- README.md +4 -3
- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -0
README.md
CHANGED
@@ -2,12 +2,13 @@
|
|
2 |
language: ger
|
3 |
license: apache-2.0
|
4 |
widget:
|
5 |
-
- text:
|
6 |
-
|
7 |
|
8 |
Der Patient hat Brustkrebs.
|
9 |
|
10 |
-
|
|
|
11 |
example_title: Patient mit Brustkreb
|
12 |
pipeline_tag: text-generation
|
13 |
---
|
|
|
2 |
language: ger
|
3 |
license: apache-2.0
|
4 |
widget:
|
5 |
+
- text: '###Context
|
6 |
+
|
7 |
|
8 |
Der Patient hat Brustkrebs.
|
9 |
|
10 |
+
|
11 |
+
###Answer'
|
12 |
example_title: Patient mit Brustkreb
|
13 |
pipeline_tag: text-generation
|
14 |
---
|
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": 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,
|
tokenizer_config.json
CHANGED
@@ -36,6 +36,7 @@
|
|
36 |
}
|
37 |
},
|
38 |
"bos_token": "<s>",
|
|
|
39 |
"clean_up_tokenization_spaces": false,
|
40 |
"eos_token": "</s>",
|
41 |
"legacy": false,
|
|
|
36 |
}
|
37 |
},
|
38 |
"bos_token": "<s>",
|
39 |
+
"chat_template": "{{bos_token}}{{'### Content\n'}}{{messages}}{{'\n\n### Answer'}}",
|
40 |
"clean_up_tokenization_spaces": false,
|
41 |
"eos_token": "</s>",
|
42 |
"legacy": false,
|