Upload tokenizer
Browse files- special_tokens_map.json +4 -0
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
@@ -1,4 +1,8 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<|im_start|>",
|
3 |
"eos_token": "<|im_end|>",
|
4 |
"pad_token": "<|im_end|>",
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
"bos_token": "<|im_start|>",
|
7 |
"eos_token": "<|im_end|>",
|
8 |
"pad_token": "<|im_end|>",
|
tokenizer_config.json
CHANGED
@@ -10,6 +10,10 @@
|
|
10 |
"special": true
|
11 |
}
|
12 |
},
|
|
|
|
|
|
|
|
|
13 |
"bos_token": "<|im_start|>",
|
14 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAIko laguntzaile lagungarria zara, GPT-Bi izenekoa, AuriLab-ek hezia.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
15 |
"clean_up_tokenization_spaces": false,
|
|
|
10 |
"special": true
|
11 |
}
|
12 |
},
|
13 |
+
"additional_special_tokens": [
|
14 |
+
"<|im_start|>",
|
15 |
+
"<|im_end|>"
|
16 |
+
],
|
17 |
"bos_token": "<|im_start|>",
|
18 |
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nAIko laguntzaile lagungarria zara, GPT-Bi izenekoa, AuriLab-ek hezia.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
19 |
"clean_up_tokenization_spaces": false,
|