Update tokenizer_config.json
Browse files- tokenizer_config.json +9 -5
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -8,7 +9,7 @@
|
|
8 |
"normalized": false,
|
9 |
"rstrip": false,
|
10 |
"single_word": false,
|
11 |
-
"special":
|
12 |
},
|
13 |
"1": {
|
14 |
"content": "<s>",
|
@@ -16,7 +17,7 @@
|
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false,
|
19 |
-
"special":
|
20 |
},
|
21 |
"2": {
|
22 |
"content": "</s>",
|
@@ -24,7 +25,7 @@
|
|
24 |
"normalized": false,
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
-
"special":
|
28 |
},
|
29 |
"32000": {
|
30 |
"content": "<|im_start|>",
|
@@ -45,13 +46,16 @@
|
|
45 |
},
|
46 |
"additional_special_tokens": [],
|
47 |
"bos_token": "<s>",
|
|
|
48 |
"clean_up_tokenization_spaces": false,
|
49 |
"eos_token": "</s>",
|
|
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
-
"pad_token":
|
52 |
"sp_model_kwargs": {},
|
53 |
"spaces_between_special_tokens": false,
|
54 |
"tokenizer_class": "LlamaTokenizer",
|
55 |
"unk_token": "<unk>",
|
56 |
-
"use_default_system_prompt": false
|
|
|
57 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
9 |
"normalized": false,
|
10 |
"rstrip": false,
|
11 |
"single_word": false,
|
12 |
+
"special": true
|
13 |
},
|
14 |
"1": {
|
15 |
"content": "<s>",
|
|
|
17 |
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false,
|
20 |
+
"special": true
|
21 |
},
|
22 |
"2": {
|
23 |
"content": "</s>",
|
|
|
25 |
"normalized": false,
|
26 |
"rstrip": false,
|
27 |
"single_word": false,
|
28 |
+
"special": true
|
29 |
},
|
30 |
"32000": {
|
31 |
"content": "<|im_start|>",
|
|
|
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": "</s>",
|
52 |
+
"legacy": true,
|
53 |
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": "</s>",
|
55 |
"sp_model_kwargs": {},
|
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 |
}
|