johannhartmann
commited on
Commit
•
1407f21
1
Parent(s):
a8bdefa
Update tokenizer_config.json
Browse files- tokenizer_config.json +23 -2
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -23,12 +25,30 @@
|
|
23 |
"rstrip": false,
|
24 |
"single_word": false,
|
25 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
|
|
27 |
},
|
28 |
"additional_special_tokens": [],
|
29 |
"bos_token": "<s>",
|
|
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
-
"eos_token": "
|
32 |
"legacy": true,
|
33 |
"model_max_length": 1000000000000000019884624838656,
|
34 |
"pad_token": null,
|
@@ -36,5 +56,6 @@
|
|
36 |
"spaces_between_special_tokens": false,
|
37 |
"tokenizer_class": "LlamaTokenizer",
|
38 |
"unk_token": "<unk>",
|
39 |
-
"use_default_system_prompt": false
|
|
|
40 |
}
|
|
|
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": true,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": true,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
}
|
45 |
+
|
46 |
},
|
47 |
"additional_special_tokens": [],
|
48 |
"bos_token": "<s>",
|
49 |
+
"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 %}",
|
50 |
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|im_end|>",
|
52 |
"legacy": true,
|
53 |
"model_max_length": 1000000000000000019884624838656,
|
54 |
"pad_token": null,
|
|
|
56 |
"spaces_between_special_tokens": false,
|
57 |
"tokenizer_class": "LlamaTokenizer",
|
58 |
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": false,
|
60 |
+
"use_fast": true
|
61 |
}
|