Upload tokenizer
Browse files- special_tokens_map.json +3 -21
- tokenizer_config.json +7 -0
special_tokens_map.json
CHANGED
|
@@ -4,26 +4,8 @@
|
|
| 4 |
"<s>",
|
| 5 |
"</s>"
|
| 6 |
],
|
| 7 |
-
"bos_token":
|
| 8 |
-
|
| 9 |
-
"lstrip": false,
|
| 10 |
-
"normalized": false,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"single_word": false
|
| 13 |
-
},
|
| 14 |
-
"eos_token": {
|
| 15 |
-
"content": "</s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": false,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false
|
| 20 |
-
},
|
| 21 |
"pad_token": "</s>",
|
| 22 |
-
"unk_token":
|
| 23 |
-
"content": "<unk>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": false,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false
|
| 28 |
-
}
|
| 29 |
}
|
|
|
|
| 4 |
"<s>",
|
| 5 |
"</s>"
|
| 6 |
],
|
| 7 |
+
"bos_token": "<s>",
|
| 8 |
+
"eos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
"pad_token": "</s>",
|
| 10 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
}
|
tokenizer_config.json
CHANGED
|
@@ -34,11 +34,18 @@
|
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": false,
|
|
|
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 38 |
"pad_token": "</s>",
|
|
|
|
|
|
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
|
|
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": true
|
| 44 |
}
|
|
|
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
"legacy": false,
|
| 37 |
+
"max_length": 4096,
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
+
"pad_to_multiple_of": null,
|
| 40 |
"pad_token": "</s>",
|
| 41 |
+
"pad_token_type_id": 0,
|
| 42 |
+
"padding_side": "left",
|
| 43 |
"sp_model_kwargs": {},
|
| 44 |
"spaces_between_special_tokens": false,
|
| 45 |
+
"stride": 0,
|
| 46 |
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
+
"truncation_side": "right",
|
| 48 |
+
"truncation_strategy": "longest_first",
|
| 49 |
"unk_token": "<unk>",
|
| 50 |
"use_default_system_prompt": true
|
| 51 |
}
|