Commit
•
eb48093
1
Parent(s):
38ffcc3
Upload tokenizer
Browse files- special_tokens_map.json +3 -22
- tokenizer.json +1 -6
- tokenizer_config.json +0 -5
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<|endoftext|>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "<|endoftext|>",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<|endoftext|>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": false,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -13,12 +13,7 @@
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
| 16 |
-
"max_length": 512,
|
| 17 |
"model_max_length": 1024,
|
| 18 |
-
"pad_token": "<|endoftext|>",
|
| 19 |
-
"stride": 0,
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
| 21 |
-
"truncation_side": "right",
|
| 22 |
-
"truncation_strategy": "longest_first",
|
| 23 |
"unk_token": "<|endoftext|>"
|
| 24 |
}
|
|
|
|
| 13 |
"bos_token": "<|endoftext|>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 16 |
"model_max_length": 1024,
|
|
|
|
|
|
|
| 17 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
|
|
|
| 18 |
"unk_token": "<|endoftext|>"
|
| 19 |
}
|