Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +2 -1
special_tokens_map.json
CHANGED
@@ -12,5 +12,12 @@
|
|
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": {
|
17 |
+
"content": "<|eot_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -2050,7 +2050,7 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
-
"chat_template": "{{
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
@@ -2059,5 +2059,6 @@
|
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 131072,
|
|
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{ bos_token }}{{ \"\" }}{% for message in messages %}{% if loop.first and message[\"role\"] != \"system\" %}{{ \"<|start_header_id|>system<|end_header_id|>\\n\\nCutting Knowledge Date: December 2023\\nToday Date: 31 Jan 2025\\n\\n\" + \"\" + \"<|eot_id|>\" }}{% endif %}{% if message[\"role\"] == \"system\" %}{{ \"<|start_header_id|>system<|end_header_id|>\\n\\nCutting Knowledge Date: December 2023\\nToday Date: 31 Jan 2025\\n\\n\" + message[\"content\"] + \"<|eot_id|>\" }}{% elif message[\"role\"] == \"user\" %}{{ \"<|start_header_id|>user<|end_header_id|>\\n\\n\" + message[\"content\"] + \"<|eot_id|>\" }}{% elif message[\"role\"] == \"assistant\" %}{{ \"<|start_header_id|>assistant<|end_header_id|>\\n\\n\" + message[\"content\"] }}{{ eos_token }}{% endif %}{% if loop.last and add_generation_prompt %}{{ \"<|start_header_id|>assistant<|end_header_id|>\\n\\n\" }}{% endif %}{% endfor %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|eot_id|>",
|
2056 |
"extra_special_tokens": {},
|
|
|
2059 |
"attention_mask"
|
2060 |
],
|
2061 |
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|eot_id|>",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
}
|