Update tokenizer_config.json
Browse files- tokenizer_config.json +10 -9
tokenizer_config.json
CHANGED
@@ -27,7 +27,7 @@
|
|
27 |
"special": true
|
28 |
},
|
29 |
"32000": {
|
30 |
-
"content": "<|
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
@@ -35,7 +35,7 @@
|
|
35 |
"special": true
|
36 |
},
|
37 |
"32001": {
|
38 |
-
"content": "<|
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
@@ -43,19 +43,20 @@
|
|
43 |
"special": true
|
44 |
}
|
45 |
},
|
46 |
-
"additional_special_tokens": [
|
47 |
-
|
48 |
-
|
|
|
|
|
|
|
49 |
"clean_up_tokenization_spaces": false,
|
50 |
-
"eos_token": "<|
|
51 |
"legacy": true,
|
52 |
"model_max_length": 1000000000000000019884624838656,
|
53 |
"pad_token": null,
|
54 |
"sp_model_kwargs": {},
|
55 |
"spaces_between_special_tokens": false,
|
56 |
"tokenizer_class": "LlamaTokenizer",
|
57 |
-
"trust_remote_code": false,
|
58 |
"unk_token": "<unk>",
|
59 |
-
"use_default_system_prompt": true
|
60 |
-
"use_fast": true
|
61 |
}
|
|
|
27 |
"special": true
|
28 |
},
|
29 |
"32000": {
|
30 |
+
"content": "<|end_of_turn|>",
|
31 |
"lstrip": false,
|
32 |
"normalized": false,
|
33 |
"rstrip": false,
|
|
|
35 |
"special": true
|
36 |
},
|
37 |
"32001": {
|
38 |
+
"content": "<|pad_0|>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
|
|
43 |
"special": true
|
44 |
}
|
45 |
},
|
46 |
+
"additional_special_tokens": [
|
47 |
+
"<|end_of_turn|>",
|
48 |
+
"<|pad_0|>"
|
49 |
+
],
|
50 |
+
"bos_token": "<s>",
|
51 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
52 |
"clean_up_tokenization_spaces": false,
|
53 |
+
"eos_token": "<|end_of_turn|>",
|
54 |
"legacy": true,
|
55 |
"model_max_length": 1000000000000000019884624838656,
|
56 |
"pad_token": null,
|
57 |
"sp_model_kwargs": {},
|
58 |
"spaces_between_special_tokens": false,
|
59 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
60 |
"unk_token": "<unk>",
|
61 |
+
"use_default_system_prompt": true
|
|
|
62 |
}
|