Commit
·
a63ff6a
1
Parent(s):
b397ead
Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer_config.json +0 -2
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
}
|
tokenizer_config.json
CHANGED
|
@@ -11,7 +11,6 @@
|
|
| 11 |
"special": true
|
| 12 |
}
|
| 13 |
},
|
| 14 |
-
"additional_special_tokens": [],
|
| 15 |
"bos_token": "<|endoftext|>",
|
| 16 |
"clean_up_tokenization_spaces": true,
|
| 17 |
"eos_token": "<|endoftext|>",
|
|
@@ -19,6 +18,5 @@
|
|
| 19 |
"model_max_length": 2048,
|
| 20 |
"pad_token": null,
|
| 21 |
"tokenizer_class": "GPT2Tokenizer",
|
| 22 |
-
"tokenizer_file": null,
|
| 23 |
"unk_token": "<|endoftext|>"
|
| 24 |
}
|
|
|
|
| 11 |
"special": true
|
| 12 |
}
|
| 13 |
},
|
|
|
|
| 14 |
"bos_token": "<|endoftext|>",
|
| 15 |
"clean_up_tokenization_spaces": true,
|
| 16 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 18 |
"model_max_length": 2048,
|
| 19 |
"pad_token": null,
|
| 20 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 21 |
"unk_token": "<|endoftext|>"
|
| 22 |
}
|