Update tokenizer_config.json
Browse files- tokenizer_config.json +4 -46
tokenizer_config.json
CHANGED
|
@@ -2047,58 +2047,16 @@
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
| 2050 |
-
},
|
| 2051 |
-
"128256": {
|
| 2052 |
-
"content": "<s>",
|
| 2053 |
-
"lstrip": false,
|
| 2054 |
-
"normalized": false,
|
| 2055 |
-
"rstrip": false,
|
| 2056 |
-
"single_word": false,
|
| 2057 |
-
"special": true
|
| 2058 |
-
},
|
| 2059 |
-
"128257": {
|
| 2060 |
-
"content": "</s>",
|
| 2061 |
-
"lstrip": false,
|
| 2062 |
-
"normalized": false,
|
| 2063 |
-
"rstrip": false,
|
| 2064 |
-
"single_word": false,
|
| 2065 |
-
"special": true
|
| 2066 |
-
},
|
| 2067 |
-
"128258": {
|
| 2068 |
-
"content": "<unk>",
|
| 2069 |
-
"lstrip": false,
|
| 2070 |
-
"normalized": false,
|
| 2071 |
-
"rstrip": false,
|
| 2072 |
-
"single_word": false,
|
| 2073 |
-
"special": true
|
| 2074 |
-
},
|
| 2075 |
-
"128259": {
|
| 2076 |
-
"content": "<|im_start|>",
|
| 2077 |
-
"lstrip": false,
|
| 2078 |
-
"normalized": false,
|
| 2079 |
-
"rstrip": false,
|
| 2080 |
-
"single_word": false,
|
| 2081 |
-
"special": false
|
| 2082 |
-
},
|
| 2083 |
-
"128260": {
|
| 2084 |
-
"content": "<|im_end|>",
|
| 2085 |
-
"lstrip": false,
|
| 2086 |
-
"normalized": false,
|
| 2087 |
-
"rstrip": false,
|
| 2088 |
-
"single_word": false,
|
| 2089 |
-
"special": false
|
| 2090 |
}
|
| 2091 |
},
|
| 2092 |
-
"bos_token": "
|
| 2093 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in
|
| 2094 |
"clean_up_tokenization_spaces": true,
|
| 2095 |
-
"eos_token": "
|
| 2096 |
"model_input_names": [
|
| 2097 |
"input_ids",
|
| 2098 |
"attention_mask"
|
| 2099 |
],
|
| 2100 |
"model_max_length": 1000000000000000019884624838656,
|
| 2101 |
-
"
|
| 2102 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 2103 |
-
"unk_token": "<unk>"
|
| 2104 |
}
|
|
|
|
| 2047 |
"rstrip": false,
|
| 2048 |
"single_word": false,
|
| 2049 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2050 |
}
|
| 2051 |
},
|
| 2052 |
+
"bos_token": "<|begin_of_text|>",
|
| 2053 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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 %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% else %}{{ eos_token }}{% endif %}",
|
| 2054 |
"clean_up_tokenization_spaces": true,
|
| 2055 |
+
"eos_token": "<|end_of_text|>",
|
| 2056 |
"model_input_names": [
|
| 2057 |
"input_ids",
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 1000000000000000019884624838656,
|
| 2061 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
| 2062 |
}
|