add chat_template
#3
by
martin-simonovsky-aa
- opened
- special_tokens_map.json +30 -1
- tokenizer_config.json +6 -1
special_tokens_map.json
CHANGED
@@ -1 +1,30 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|padding|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|unknown|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
CHANGED
@@ -6593,7 +6593,12 @@
|
|
6593 |
"special": true
|
6594 |
}
|
6595 |
},
|
|
|
|
|
|
|
|
|
|
|
6596 |
"clean_up_tokenization_spaces": true,
|
6597 |
"model_max_length": 1000000000000000019884624838656,
|
6598 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
6599 |
-
}
|
|
|
6593 |
"special": true
|
6594 |
}
|
6595 |
},
|
6596 |
+
"bos_token": "<|begin_of_text|>",
|
6597 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
|
6598 |
+
"eos_token": "<|endoftext|>",
|
6599 |
+
"pad_token": "<|padding|>",
|
6600 |
+
"unk_token": "<|unknown|>",
|
6601 |
"clean_up_tokenization_spaces": true,
|
6602 |
"model_max_length": 1000000000000000019884624838656,
|
6603 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
6604 |
+
}
|