falcon-7b-i-QLoRa-HL_pdfs / tokenizer_config.json
lalafenno's picture
Upload tokenizer
a62276e verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": ">>TITLE<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": ">>ABSTRACT<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": ">>INTRODUCTION<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": ">>SUMMARY<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": ">>COMMENT<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": ">>ANSWER<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": ">>QUESTION<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": ">>DOMAIN<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": ">>PREFIX<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": ">>SUFFIX<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"10": {
"content": ">>MIDDLE<<",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"11": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
">>TITLE<<",
">>ABSTRACT<<",
">>INTRODUCTION<<",
">>SUMMARY<<",
">>COMMENT<<",
">>ANSWER<<",
">>QUESTION<<",
">>DOMAIN<<",
">>PREFIX<<",
">>SUFFIX<<",
">>MIDDLE<<"
],
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 2048,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}