Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +18 -0
- tokenizer_config.json +21 -3
special_tokens_map.json
CHANGED
@@ -7,7 +7,7 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -29,6 +29,24 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 32000,
|
35 |
+
"content": "<|im_end|>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 32001,
|
44 |
+
"content": "<|im_start|>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,19 +25,37 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
"additional_special_tokens": [],
|
31 |
"bos_token": "<s>",
|
32 |
-
"chat_template": "{
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
-
"eos_token": "
|
35 |
"legacy": true,
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
"pad_token": null,
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
41 |
"unk_token": "<unk>",
|
42 |
-
"use_default_system_prompt":
|
|
|
43 |
}
|
|
|
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,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
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": 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 |
}
|