File size: 1,389 Bytes
4aa2077 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 | {
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|end_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"extra_special_tokens": {},
"eos_token_id": 2,
"eos_token": "<|end_of_text|>",
"chat_template": "{%- for message in messages %}\n{{- '<|im_start|>' + message.role + '\\n' }}\n{%- if message.content is string %}\n{{- message.content }}\n{%- else %}\n{%- for content in message.content %}\n{%- if 'text' in content %}\n{{- content.text }}\n{%- endif %}\n{%- endfor %}\n{%- endif %}\n{{- '<|im_end|>\\n' }}\n{%- endfor %}\n{%- if add_generation_prompt %}\n{{- '<|im_start|>assistant\\n<think>' }}\n{%- endif %}\n",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "PreTrainedTokenizerFast"
}
|