DeepMount00
commited on
Upload tokenizer
Browse files- special_tokens_map.json +1 -8
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
@@ -3,13 +3,6 @@
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
6 |
-
"bos_token": {
|
7 |
-
"content": "<|im_start|>",
|
8 |
-
"lstrip": false,
|
9 |
-
"normalized": false,
|
10 |
-
"rstrip": false,
|
11 |
-
"single_word": false
|
12 |
-
},
|
13 |
"eos_token": {
|
14 |
"content": "<|im_end|>",
|
15 |
"lstrip": false,
|
@@ -18,7 +11,7 @@
|
|
18 |
"single_word": false
|
19 |
},
|
20 |
"pad_token": {
|
21 |
-
"content": "<|
|
22 |
"lstrip": false,
|
23 |
"normalized": false,
|
24 |
"rstrip": false,
|
|
|
3 |
"<|im_start|>",
|
4 |
"<|im_end|>"
|
5 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"eos_token": {
|
7 |
"content": "<|im_end|>",
|
8 |
"lstrip": false,
|
|
|
11 |
"single_word": false
|
12 |
},
|
13 |
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
tokenizer_config.json
CHANGED
@@ -30,13 +30,13 @@
|
|
30 |
"<|im_start|>",
|
31 |
"<|im_end|>"
|
32 |
],
|
33 |
-
"bos_token":
|
34 |
-
"chat_template": "{% for message in messages %}{{'<|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": "<|im_end|>",
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 32768,
|
39 |
-
"pad_token": "<|
|
40 |
"split_special_tokens": false,
|
41 |
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
"unk_token": null
|
|
|
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": "<|im_end|>",
|
37 |
"errors": "replace",
|
38 |
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
"split_special_tokens": false,
|
41 |
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
"unk_token": null
|