Upload tokenizer
Browse files- special_tokens_map.json +1 -14
- tokenizer.json +0 -0
- tokenizer_config.json +0 -3
special_tokens_map.json
CHANGED
|
@@ -1,16 +1,3 @@
|
|
| 1 |
{
|
| 2 |
-
"eos_token":
|
| 3 |
-
"content": "<|endoftext|>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"pad_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
}
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"eos_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_eos_token": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<|endoftext|>",
|
|
@@ -10,11 +9,9 @@
|
|
| 10 |
"special": true
|
| 11 |
}
|
| 12 |
},
|
| 13 |
-
"bos_token": null,
|
| 14 |
"clean_up_tokenization_spaces": false,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
"extra_special_tokens": {},
|
| 17 |
"model_max_length": 1000000000000000019884624838656,
|
| 18 |
-
"pad_token": "<|endoftext|>",
|
| 19 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 20 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<|endoftext|>",
|
|
|
|
| 9 |
"special": true
|
| 10 |
}
|
| 11 |
},
|
|
|
|
| 12 |
"clean_up_tokenization_spaces": false,
|
| 13 |
"eos_token": "<|endoftext|>",
|
| 14 |
"extra_special_tokens": {},
|
| 15 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 16 |
"tokenizer_class": "PreTrainedTokenizer"
|
| 17 |
}
|