Commit
•
397a9ed
1
Parent(s):
db84dbf
Upload tokenizer
Browse files- merges.txt +0 -0
- special_tokens_map.json +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": "<unk>"
|
| 3 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
+
"model_max_length": 512,
|
| 14 |
+
"tokenizer_class": "OpenAIGPTTokenizer",
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|