Update tokenizer_config.json
Browse files- tokenizer_config.json +10 -5
tokenizer_config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"151643": {
|
4 |
"content": "<|endoftext|>",
|
@@ -25,11 +26,15 @@
|
|
25 |
"special": true
|
26 |
}
|
27 |
},
|
|
|
28 |
"bos_token": null,
|
29 |
-
"
|
30 |
-
"
|
31 |
-
"
|
|
|
|
|
32 |
"pad_token": "<|endoftext|>",
|
|
|
33 |
"tokenizer_class": "Qwen2Tokenizer",
|
34 |
-
"unk_token":
|
35 |
-
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
"added_tokens_decoder": {
|
4 |
"151643": {
|
5 |
"content": "<|endoftext|>",
|
|
|
26 |
"special": true
|
27 |
}
|
28 |
},
|
29 |
+
"additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
|
30 |
"bos_token": null,
|
31 |
+
"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 %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "<|im_end|>",
|
34 |
+
"errors": "replace",
|
35 |
+
"model_max_length": 32768,
|
36 |
"pad_token": "<|endoftext|>",
|
37 |
+
"split_special_tokens": false,
|
38 |
"tokenizer_class": "Qwen2Tokenizer",
|
39 |
+
"unk_token": null
|
40 |
+
}
|