Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer_config.json +5 -12
special_tokens_map.json
CHANGED
|
@@ -14,7 +14,7 @@
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
-
"content": "<
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
|
|
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
"pad_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
"lstrip": false,
|
| 19 |
"normalized": false,
|
| 20 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -25,25 +25,18 @@
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
| 28 |
-
},
|
| 29 |
-
"32000": {
|
| 30 |
-
"content": "<pad>",
|
| 31 |
-
"lstrip": false,
|
| 32 |
-
"normalized": false,
|
| 33 |
-
"rstrip": false,
|
| 34 |
-
"single_word": false,
|
| 35 |
-
"special": true
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"bos_token": "<s>",
|
| 39 |
"clean_up_tokenization_spaces": false,
|
| 40 |
"eos_token": "</s>",
|
| 41 |
-
"legacy":
|
| 42 |
-
"model_max_length":
|
| 43 |
-
"pad_token": "<
|
|
|
|
| 44 |
"sp_model_kwargs": {},
|
| 45 |
"spaces_between_special_tokens": false,
|
| 46 |
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
"unk_token": "<unk>",
|
| 48 |
-
"use_default_system_prompt":
|
| 49 |
}
|
|
|
|
| 25 |
"rstrip": false,
|
| 26 |
"single_word": false,
|
| 27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
| 29 |
},
|
| 30 |
"bos_token": "<s>",
|
| 31 |
"clean_up_tokenization_spaces": false,
|
| 32 |
"eos_token": "</s>",
|
| 33 |
+
"legacy": false,
|
| 34 |
+
"model_max_length": 4096,
|
| 35 |
+
"pad_token": "<unk>",
|
| 36 |
+
"padding_side": "right",
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
}
|