Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -2
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 50257
|
| 3 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -13,6 +13,7 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": "[PAD]",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -9,6 +9,7 @@
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
|
|
|
| 12 |
"eos_token": {
|
| 13 |
"__type": "AddedToken",
|
| 14 |
"content": "<|endoftext|>",
|
|
@@ -19,9 +20,7 @@
|
|
| 19 |
},
|
| 20 |
"errors": "replace",
|
| 21 |
"model_max_length": 1024,
|
| 22 |
-
"name_or_path": "./fine_tuned_gpt2",
|
| 23 |
"pad_token": null,
|
| 24 |
-
"special_tokens_map_file": null,
|
| 25 |
"tokenizer_class": "GPT2Tokenizer",
|
| 26 |
"unk_token": {
|
| 27 |
"__type": "AddedToken",
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
"single_word": false
|
| 11 |
},
|
| 12 |
+
"clean_up_tokenization_spaces": true,
|
| 13 |
"eos_token": {
|
| 14 |
"__type": "AddedToken",
|
| 15 |
"content": "<|endoftext|>",
|
|
|
|
| 20 |
},
|
| 21 |
"errors": "replace",
|
| 22 |
"model_max_length": 1024,
|
|
|
|
| 23 |
"pad_token": null,
|
|
|
|
| 24 |
"tokenizer_class": "GPT2Tokenizer",
|
| 25 |
"unk_token": {
|
| 26 |
"__type": "AddedToken",
|