Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +3 -1
special_tokens_map.json
CHANGED
@@ -48,6 +48,13 @@
|
|
48 |
"rstrip": false,
|
49 |
"single_word": false
|
50 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
"unk_token": {
|
52 |
"content": "<|endoftext|>",
|
53 |
"lstrip": false,
|
|
|
48 |
"rstrip": false,
|
49 |
"single_word": false
|
50 |
},
|
51 |
+
"pad_token": {
|
52 |
+
"content": "<|endoftext|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false
|
57 |
+
},
|
58 |
"unk_token": {
|
59 |
"content": "<|endoftext|>",
|
60 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -302,9 +302,11 @@
|
|
302 |
"<|extra0|>"
|
303 |
],
|
304 |
"bos_token": "<|endoftext|>",
|
|
|
305 |
"clean_up_tokenization_spaces": true,
|
306 |
"eos_token": "<|endoftext|>",
|
307 |
-
"model_max_length":
|
|
|
308 |
"tokenizer_class": "GPT2Tokenizer",
|
309 |
"unk_token": "<|endoftext|>"
|
310 |
}
|
|
|
302 |
"<|extra0|>"
|
303 |
],
|
304 |
"bos_token": "<|endoftext|>",
|
305 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
306 |
"clean_up_tokenization_spaces": true,
|
307 |
"eos_token": "<|endoftext|>",
|
308 |
+
"model_max_length": 2048,
|
309 |
+
"pad_token": "<|endoftext|>",
|
310 |
"tokenizer_class": "GPT2Tokenizer",
|
311 |
"unk_token": "<|endoftext|>"
|
312 |
}
|