Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +20 -5
special_tokens_map.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
"pad_token": "<|endoftext|>",
|
| 5 |
-
"unk_token": "
|
| 6 |
}
|
|
|
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
"eos_token": "<|endoftext|>",
|
| 4 |
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,10 +1,25 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
|
@@ -13,8 +28,8 @@
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
-
"model_max_length":
|
| 17 |
"pad_token": "<|endoftext|>",
|
| 18 |
-
"tokenizer_class": "
|
| 19 |
-
"unk_token": "
|
| 20 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<|endoftext|>",
|
| 5 |
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<unk>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<pad>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
"special": true
|
|
|
|
| 28 |
"bos_token": "<|endoftext|>",
|
| 29 |
"clean_up_tokenization_spaces": true,
|
| 30 |
"eos_token": "<|endoftext|>",
|
| 31 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 32 |
"pad_token": "<|endoftext|>",
|
| 33 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 34 |
+
"unk_token": "<unk>"
|
| 35 |
}
|