Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -23
tokenizer_config.json
CHANGED
@@ -23,36 +23,17 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
-
},
|
27 |
-
"32000": {
|
28 |
-
"content": "<|im_end|>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"32001": {
|
36 |
-
"content": "<|im_start|>",
|
37 |
-
"lstrip": true,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": true,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
}
|
43 |
},
|
44 |
"additional_special_tokens": [
|
45 |
"<unk>",
|
46 |
"<s>",
|
47 |
-
"</s>"
|
48 |
-
"<|im_end|>",
|
49 |
-
"<|im_start|>"
|
50 |
],
|
51 |
"bos_token": "<s>",
|
52 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
53 |
"clean_up_tokenization_spaces": false,
|
54 |
-
"eos_token": "
|
55 |
-
"legacy":
|
56 |
"model_max_length": 1000000000000000019884624838656,
|
57 |
"pad_token": null,
|
58 |
"sp_model_kwargs": {},
|
@@ -62,4 +43,4 @@
|
|
62 |
"unk_token": "<unk>",
|
63 |
"use_default_system_prompt": true,
|
64 |
"use_fast": true
|
65 |
-
}
|
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
"additional_special_tokens": [
|
29 |
"<unk>",
|
30 |
"<s>",
|
31 |
+
"</s>"
|
|
|
|
|
32 |
],
|
33 |
"bos_token": "<s>",
|
|
|
34 |
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": false,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
"pad_token": null,
|
39 |
"sp_model_kwargs": {},
|
|
|
43 |
"unk_token": "<unk>",
|
44 |
"use_default_system_prompt": true,
|
45 |
"use_fast": true
|
46 |
+
}
|