Upload tokenizer
Browse files- README.md +1 -1
- special_tokens_map.json +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +1 -2
README.md
CHANGED
|
@@ -14,4 +14,4 @@ tags:
|
|
| 14 |
- fine-tuned
|
| 15 |
- custom-dataset
|
| 16 |
- text-generation
|
| 17 |
-
---
|
|
|
|
| 14 |
- fine-tuned
|
| 15 |
- custom-dataset
|
| 16 |
- text-generation
|
| 17 |
+
---
|
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,6 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token": "<|endoftext|>",
|
| 17 |
"unk_token": {
|
| 18 |
"content": "<|endoftext|>",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 16 |
"unk_token": {
|
| 17 |
"content": "<|endoftext|>",
|
| 18 |
"lstrip": false,
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -15,9 +15,8 @@
|
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
"eos_token": "<|endoftext|>",
|
| 17 |
"errors": "replace",
|
| 18 |
-
"extra_special_tokens": {},
|
| 19 |
"model_max_length": 2048,
|
| 20 |
-
"pad_token":
|
| 21 |
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
"unk_token": "<|endoftext|>"
|
| 23 |
}
|
|
|
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
"eos_token": "<|endoftext|>",
|
| 17 |
"errors": "replace",
|
|
|
|
| 18 |
"model_max_length": 2048,
|
| 19 |
+
"pad_token": null,
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
"unk_token": "<|endoftext|>"
|
| 22 |
}
|