Update tokenizer_config.json
#1
by
saattrupdan
- opened
- tokenizer_config.json +25 -6
tokenizer_config.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
@@ -19,7 +19,23 @@
|
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
-
"content": "
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"lstrip": false,
|
24 |
"normalized": false,
|
25 |
"rstrip": false,
|
@@ -28,15 +44,18 @@
|
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
-
"bos_token": "
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
-
"eos_token": "
|
34 |
"legacy": true,
|
35 |
-
"model_max_length":
|
36 |
"pad_token": null,
|
37 |
"sp_model_kwargs": {},
|
38 |
"spaces_between_special_tokens": false,
|
39 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
40 |
"unk_token": "<unk>",
|
41 |
-
"use_default_system_prompt":
|
|
|
42 |
}
|
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
|
|
19 |
"special": true
|
20 |
},
|
21 |
"2": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<|im_end|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<|im_start|>",
|
39 |
"lstrip": false,
|
40 |
"normalized": false,
|
41 |
"rstrip": false,
|
|
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
+
"bos_token": "<|im_start|>",
|
48 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
49 |
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "<|im_end|>",
|
51 |
"legacy": true,
|
52 |
+
"model_max_length": 32768,
|
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 |
}
|