idefics2-open-i-dataset / tokenizer_config.json
dmusingu's picture
Training done
e585c95 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": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<fake_token_around_image>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "<image>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<end_of_utterance>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<fake_token_around_image>",
"<image>",
"<end_of_utterance>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"do_image_splitting": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"processor_class": "Idefics2Processor",
"size": {
"longest_edge": 448,
"shortest_edge": 378
},
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": true
}