andykcheng
commited on
Commit
•
1d61f5e
1
Parent(s):
0bd6c76
Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer.json +0 -27
- tokenizer_config.json +4 -28
special_tokens_map.json
CHANGED
@@ -14,10 +14,10 @@
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
-
"lstrip":
|
19 |
"normalized": false,
|
20 |
-
"rstrip":
|
21 |
"single_word": false
|
22 |
},
|
23 |
"unk_token": {
|
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"unk_token": {
|
tokenizer.json
CHANGED
@@ -29,33 +29,6 @@
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
32 |
-
},
|
33 |
-
{
|
34 |
-
"id": 32000,
|
35 |
-
"content": "[PAD]",
|
36 |
-
"single_word": false,
|
37 |
-
"lstrip": true,
|
38 |
-
"rstrip": true,
|
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 |
-
"id": 32002,
|
53 |
-
"content": "<|im_end|>",
|
54 |
-
"single_word": false,
|
55 |
-
"lstrip": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"normalized": false,
|
58 |
-
"special": true
|
59 |
}
|
60 |
],
|
61 |
"normalizer": {
|
|
|
29 |
"rstrip": false,
|
30 |
"normalized": false,
|
31 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
}
|
33 |
],
|
34 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -23,42 +23,18 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
26 |
-
},
|
27 |
-
"32000": {
|
28 |
-
"content": "[PAD]",
|
29 |
-
"lstrip": true,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": true,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"32001": {
|
36 |
-
"content": "<|im_start|>",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"32002": {
|
44 |
-
"content": "<|im_end|>",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
}
|
51 |
},
|
52 |
-
"additional_special_tokens": [],
|
53 |
"bos_token": "<s>",
|
|
|
54 |
"clean_up_tokenization_spaces": false,
|
55 |
"eos_token": "</s>",
|
56 |
"legacy": false,
|
57 |
-
"model_max_length":
|
58 |
-
"pad_token": "
|
59 |
"padding_side": "right",
|
60 |
"sp_model_kwargs": {},
|
61 |
"tokenizer_class": "LlamaTokenizer",
|
62 |
"unk_token": "<unk>",
|
63 |
-
"use_default_system_prompt":
|
64 |
}
|
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
|
|
28 |
"bos_token": "<s>",
|
29 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
"legacy": false,
|
33 |
+
"model_max_length": 2048,
|
34 |
+
"pad_token": "</s>",
|
35 |
"padding_side": "right",
|
36 |
"sp_model_kwargs": {},
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
"unk_token": "<unk>",
|
39 |
+
"use_default_system_prompt": false
|
40 |
}
|