Upload tokenizer
Browse files- tokenizer.json +1 -2
- tokenizer_config.json +0 -11
tokenizer.json
CHANGED
|
@@ -23,7 +23,7 @@
|
|
| 23 |
"single_word": false,
|
| 24 |
"lstrip": false,
|
| 25 |
"rstrip": false,
|
| 26 |
-
"normalized":
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
],
|
|
@@ -54,7 +54,6 @@
|
|
| 54 |
"end_of_word_suffix": "",
|
| 55 |
"fuse_unk": false,
|
| 56 |
"byte_fallback": false,
|
| 57 |
-
"ignore_merges": false,
|
| 58 |
"vocab": {
|
| 59 |
"!": 0,
|
| 60 |
"\"": 1,
|
|
|
|
| 23 |
"single_word": false,
|
| 24 |
"lstrip": false,
|
| 25 |
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
"special": true
|
| 28 |
}
|
| 29 |
],
|
|
|
|
| 54 |
"end_of_word_suffix": "",
|
| 55 |
"fuse_unk": false,
|
| 56 |
"byte_fallback": false,
|
|
|
|
| 57 |
"vocab": {
|
| 58 |
"!": 0,
|
| 59 |
"\"": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,20 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"50256": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
}
|
| 12 |
-
},
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
"model_max_length": 1024,
|
| 17 |
-
"pad_token": "<|endoftext|>",
|
| 18 |
"tokenizer_class": "GPT2Tokenizer",
|
| 19 |
"unk_token": "<|endoftext|>"
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 1024,
|
|
|
|
| 7 |
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
"unk_token": "<|endoftext|>"
|
| 9 |
}
|