LoneStriker
commited on
Commit
•
e52cfed
1
Parent(s):
cccbd24
Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -3
tokenizer_config.json
CHANGED
@@ -25,16 +25,17 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
|
|
28 |
"bos_token": "<s>",
|
29 |
"clean_up_tokenization_spaces": false,
|
30 |
"eos_token": "</s>",
|
31 |
-
"legacy":
|
32 |
"model_max_length": 1000000000000000019884624838656,
|
33 |
"pad_token": null,
|
34 |
-
"padding_side": "right",
|
35 |
"sp_model_kwargs": {},
|
|
|
36 |
"tokenizer_class": "LlamaTokenizer",
|
37 |
"unk_token": "<unk>",
|
38 |
"use_default_system_prompt": false,
|
39 |
-
"chat_template": "{
|
40 |
}
|
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
28 |
+
"additional_special_tokens": [],
|
29 |
"bos_token": "<s>",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
+
"legacy": true,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
"pad_token": null,
|
|
|
35 |
"sp_model_kwargs": {},
|
36 |
+
"spaces_between_special_tokens": false,
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
"unk_token": "<unk>",
|
39 |
"use_default_system_prompt": false,
|
40 |
+
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}\n"
|
41 |
}
|