sshukla4 commited on
Commit
a59ca8f
·
verified ·
1 Parent(s): 475d09f

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +45 -44
tokenizer_config.json CHANGED
@@ -1,44 +1,45 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "151643": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "151644": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "151645": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- }
28
- },
29
- "additional_special_tokens": [
30
- "<|im_start|>",
31
- "<|im_end|>"
32
- ],
33
- "bos_token": null,
34
- "clean_up_tokenization_spaces": false,
35
- "eos_token": "<|endoftext|>",
36
- "errors": "replace",
37
- "extra_special_tokens": {},
38
- "model_max_length": 32768,
39
- "pad_token": "<|endoftext|>",
40
- "padding_side": "left",
41
- "split_special_tokens": false,
42
- "tokenizer_class": "Qwen2Tokenizer",
43
- "unk_token": null
44
- }
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "extra_special_tokens": {},
39
+ "model_max_length": 32768,
40
+ "pad_token": "<|endoftext|>",
41
+ "padding_side": "left",
42
+ "split_special_tokens": false,
43
+ "tokenizer_class": "Qwen2Tokenizer",
44
+ "unk_token": null
45
+ }