danielhanchen
commited on
Commit
•
25223dd
1
Parent(s):
0480a64
Upload tokenizer
Browse files- special_tokens_map.json +2 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -12,5 +12,6 @@
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
-
}
|
|
|
16 |
}
|
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|end_of_text|>"
|
17 |
}
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,6 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"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' }}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|end_of_text|>",
|
2056 |
"model_input_names": [
|
@@ -2058,6 +2057,7 @@
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 8192,
|
|
|
2061 |
"padding_side": "right",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
"eos_token": "<|end_of_text|>",
|
2055 |
"model_input_names": [
|
|
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 8192,
|
2060 |
+
"pad_token": "<|end_of_text|>",
|
2061 |
"padding_side": "right",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|