phi-3-vision-tokenizer / tokenizer_config.json
Sabeerali's picture
Upload tokenizer
820f3ab verified
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<|assistant|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"4": {
"content": "<|placeholder1|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"5": {
"content": "<|placeholder2|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"6": {
"content": "<|placeholder3|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"7": {
"content": "<|placeholder4|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"8": {
"content": "<|system|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<|end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": "<|placeholder5|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"11": {
"content": "<|placeholder6|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"12": {
"content": "<|user|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"13": {
"content": "<|placeholder7|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"14": {
"content": "<|placeholder8|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"15": {
"content": "<|placeholder9|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"16": {
"content": "<|placeholder10|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"17": {
"content": "<|placeholder11|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"18": {
"content": "<|placeholder12|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"19": {
"content": "<|placeholder13|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"20": {
"content": "<|placeholder14|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"21": {
"content": "<|placeholder15|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"22": {
"content": "<|placeholder16|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"23": {
"content": "<|placeholder17|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"24": {
"content": "<|placeholder18|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"25": {
"content": "<|placeholder19|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"26": {
"content": "<|placeholder20|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"27": {
"content": "<|placeholder21|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"28": {
"content": "<|placeholder22|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"29": {
"content": "<|placeholder23|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"30": {
"content": "<|placeholder24|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"31": {
"content": "<|placeholder25|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"32": {
"content": "<|placeholder26|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"33": {
"content": "<|placeholder27|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"34": {
"content": "<|placeholder28|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"35": {
"content": "<|placeholder29|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"36": {
"content": "<|placeholder30|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"37": {
"content": "<|placeholder31|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"38": {
"content": "<|placeholder32|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"39": {
"content": "<|placeholder33|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"40": {
"content": "<|placeholder34|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"41": {
"content": "<|placeholder35|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"42": {
"content": "<|placeholder36|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"43": {
"content": "<|placeholder37|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"44": {
"content": "<|placeholder38|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"45": {
"content": "<|placeholder39|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"46": {
"content": "<|image|>",
"lstrip": false,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|system|>",
"<|end|>",
"<|user|>",
"<|end|>"
],
"bos_token": "<s>",
"chat_template": "{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{- '<|assistant|>\n' -}}{% endif %}",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"legacy": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"sp_model_kwargs": {},
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}