Sławomir Dadas
commited on
Commit
•
0ecf713
1
Parent(s):
3103539
add tokenizer
Browse files- special_tokens_map.json +5 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"bos_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"name_or_path": "original/polish-gpt2-medium",
|
| 8 |
+
"special_tokens_map_file": "original/polish-gpt2-medium/special_tokens_map.json",
|
| 9 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
+
"unk_token": "<unk>"
|
| 11 |
+
}
|