Upload tokenizer
Browse files- special_tokens_map.json +2 -2
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
|
@@ -23,11 +23,11 @@
|
|
| 23 |
"single_word": false
|
| 24 |
},
|
| 25 |
"eos_token": {
|
| 26 |
-
"content": "<|
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
},
|
| 32 |
-
"pad_token": "<|
|
| 33 |
}
|
|
|
|
| 23 |
"single_word": false
|
| 24 |
},
|
| 25 |
"eos_token": {
|
| 26 |
+
"content": "<|end_of_text|>",
|
| 27 |
"lstrip": false,
|
| 28 |
"normalized": false,
|
| 29 |
"rstrip": false,
|
| 30 |
"single_word": false
|
| 31 |
},
|
| 32 |
+
"pad_token": "<|end_of_text|>"
|
| 33 |
}
|
tokenizer_config.json
CHANGED
|
@@ -2054,16 +2054,16 @@
|
|
| 2054 |
"<|eom_id|>"
|
| 2055 |
],
|
| 2056 |
"bos_token": "<|begin_of_text|>",
|
| 2057 |
-
"chat_template": "{{
|
| 2058 |
"clean_up_tokenization_spaces": true,
|
| 2059 |
-
"eos_token": "<|
|
| 2060 |
"extra_special_tokens": {},
|
| 2061 |
"model_input_names": [
|
| 2062 |
"input_ids",
|
| 2063 |
"attention_mask"
|
| 2064 |
],
|
| 2065 |
"model_max_length": 131072,
|
| 2066 |
-
"pad_token": "<|
|
| 2067 |
"padding_side": "left",
|
| 2068 |
"split_special_tokens": false,
|
| 2069 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
| 2054 |
"<|eom_id|>"
|
| 2055 |
],
|
| 2056 |
"bos_token": "<|begin_of_text|>",
|
| 2057 |
+
"chat_template": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
|
| 2058 |
"clean_up_tokenization_spaces": true,
|
| 2059 |
+
"eos_token": "<|end_of_text|>",
|
| 2060 |
"extra_special_tokens": {},
|
| 2061 |
"model_input_names": [
|
| 2062 |
"input_ids",
|
| 2063 |
"attention_mask"
|
| 2064 |
],
|
| 2065 |
"model_max_length": 131072,
|
| 2066 |
+
"pad_token": "<|end_of_text|>",
|
| 2067 |
"padding_side": "left",
|
| 2068 |
"split_special_tokens": false,
|
| 2069 |
"tokenizer_class": "PreTrainedTokenizerFast"
|