J.O.S.I.E.-x-Qwen1.5-1.8B-Chat / tokenizer_config.json
Isaak Carter Augustus
Upload tokenizer
d2441b7 verified
raw
history blame
No virus
5.67 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"151643": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151644": {
"content": "<|im_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151645": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151646": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|functions|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|gökdeniz|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|josie|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|function_call|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|function_response|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|image|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|long_term_memory|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|short_term_memory|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<|home_state|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151658": {
"content": "<|current_states|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151659": {
"content": "<|context|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151660": {
"content": "Gökdeniz Gülmez",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "Gökdeniz",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "Gülmez",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "JOSIE",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "J.O.S.I.E.",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151665": {
"content": "Josie",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151666": {
"content": "josie",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"151667": {
"content": "Just an Outstandingly Smart and Intelligent Entity",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|functions|>",
"<|gökdeniz|>",
"<|user|>",
"<|josie|>",
"<|assistant|>",
"<|function_call|>",
"<|function_response|>",
"<|image|>",
"<|long_term_memory|>",
"<|short_term_memory|>",
"<|home_state|>",
"<|current_states|>",
"<|context|>"
],
"bos_token": "<|startoftext|>",
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}