Update tokeniser
Browse files- added_tokens.json +4 -0
- config.json +1 -1
- special_tokens_map.json +2 -8
- tokenizer_config.json +22 -2
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|im_end|>": 32000,
|
3 |
+
"<|im_start|>": 32001
|
4 |
+
}
|
config.json
CHANGED
@@ -24,5 +24,5 @@
|
|
24 |
"torch_dtype": "float16",
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": true,
|
27 |
-
"vocab_size":
|
28 |
}
|
|
|
24 |
"torch_dtype": "float16",
|
25 |
"transformers_version": "4.34.1",
|
26 |
"use_cache": true,
|
27 |
+
"vocab_size": 32002
|
28 |
}
|
special_tokens_map.json
CHANGED
@@ -7,19 +7,13 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
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": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|im_end|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "</s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -23,11 +25,27 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
},
|
28 |
"additional_special_tokens": [],
|
29 |
"bos_token": "<s>",
|
30 |
-
|
31 |
"clean_up_tokenization_spaces": false,
|
32 |
"eos_token": "</s>",
|
33 |
"legacy": true,
|
@@ -36,6 +54,8 @@
|
|
36 |
"sp_model_kwargs": {},
|
37 |
"spaces_between_special_tokens": false,
|
38 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
39 |
"unk_token": "<unk>",
|
40 |
-
"use_default_system_prompt": true
|
|
|
41 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
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": false
|
44 |
}
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
48 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n' + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
|
49 |
"clean_up_tokenization_spaces": false,
|
50 |
"eos_token": "</s>",
|
51 |
"legacy": true,
|
|
|
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 |
}
|