Update tokenizer_config.json
Browse files- tokenizer_config.json +1 -48
tokenizer_config.json
CHANGED
|
@@ -1,51 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"added_tokens_decoder": {
|
| 3 |
-
"0": {
|
| 4 |
-
"content": "<unk>",
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": false,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false,
|
| 9 |
-
"special": true
|
| 10 |
-
},
|
| 11 |
-
"1": {
|
| 12 |
-
"content": "<s>",
|
| 13 |
-
"lstrip": false,
|
| 14 |
-
"normalized": false,
|
| 15 |
-
"rstrip": false,
|
| 16 |
-
"single_word": false,
|
| 17 |
-
"special": true
|
| 18 |
-
},
|
| 19 |
-
"2": {
|
| 20 |
-
"content": "</s>",
|
| 21 |
-
"lstrip": false,
|
| 22 |
-
"normalized": false,
|
| 23 |
-
"rstrip": false,
|
| 24 |
-
"single_word": false,
|
| 25 |
-
"special": true
|
| 26 |
-
},
|
| 27 |
-
"32000": {
|
| 28 |
-
"content": "<|im_start|>",
|
| 29 |
-
"lstrip": false,
|
| 30 |
-
"normalized": false,
|
| 31 |
-
"rstrip": false,
|
| 32 |
-
"single_word": false,
|
| 33 |
-
"special": true
|
| 34 |
-
},
|
| 35 |
-
"32001": {
|
| 36 |
-
"content": "<|im_end|>",
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
}
|
| 43 |
-
},
|
| 44 |
-
"additional_special_tokens": [
|
| 45 |
-
"<unk>",
|
| 46 |
-
"<s>",
|
| 47 |
-
"</s>"
|
| 48 |
-
],
|
| 49 |
"bos_token": "<s>",
|
| 50 |
"clean_up_tokenization_spaces": false,
|
| 51 |
"eos_token": "</s>",
|
|
@@ -56,5 +9,5 @@
|
|
| 56 |
"spaces_between_special_tokens": false,
|
| 57 |
"tokenizer_class": "LlamaTokenizer",
|
| 58 |
"unk_token": "<unk>",
|
| 59 |
-
"use_default_system_prompt":
|
| 60 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "<s>",
|
| 3 |
"clean_up_tokenization_spaces": false,
|
| 4 |
"eos_token": "</s>",
|
|
|
|
| 9 |
"spaces_between_special_tokens": false,
|
| 10 |
"tokenizer_class": "LlamaTokenizer",
|
| 11 |
"unk_token": "<unk>",
|
| 12 |
+
"use_default_system_prompt": false
|
| 13 |
}
|