Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -9
special_tokens_map.json
CHANGED
|
@@ -16,7 +16,13 @@
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"unk_token": {
|
| 21 |
"content": "<|unknown|>",
|
| 22 |
"lstrip": false,
|
|
|
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false
|
| 18 |
},
|
| 19 |
+
"pad_token": {
|
| 20 |
+
"content": "<|pad|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false
|
| 25 |
+
},
|
| 26 |
"unk_token": {
|
| 27 |
"content": "<|unknown|>",
|
| 28 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -41,14 +41,6 @@
|
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false,
|
| 43 |
"special": true
|
| 44 |
-
},
|
| 45 |
-
"65535": {
|
| 46 |
-
"content": "[PAD]",
|
| 47 |
-
"lstrip": false,
|
| 48 |
-
"normalized": false,
|
| 49 |
-
"rstrip": false,
|
| 50 |
-
"single_word": false,
|
| 51 |
-
"special": true
|
| 52 |
}
|
| 53 |
},
|
| 54 |
"additional_special_tokens": [
|
|
@@ -59,7 +51,7 @@
|
|
| 59 |
"eos_token": "<|endoftext|>",
|
| 60 |
"legacy": true,
|
| 61 |
"model_max_length": 8192,
|
| 62 |
-
"pad_token": "<|
|
| 63 |
"sp_model_kwargs": {},
|
| 64 |
"spaces_between_special_tokens": false,
|
| 65 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false,
|
| 43 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
}
|
| 45 |
},
|
| 46 |
"additional_special_tokens": [
|
|
|
|
| 51 |
"eos_token": "<|endoftext|>",
|
| 52 |
"legacy": true,
|
| 53 |
"model_max_length": 8192,
|
| 54 |
+
"pad_token": "<|pad|>",
|
| 55 |
"sp_model_kwargs": {},
|
| 56 |
"spaces_between_special_tokens": false,
|
| 57 |
"tokenizer_class": "LlamaTokenizer",
|