YaHaHamaraLlama / tokenizer_config.json
bilkultheek's picture
Training in progress, step 625
797c227 verified
raw
history blame contribute delete
826 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"1": {
"content": "\"",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "#",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "#",
"errors": "replace",
"model_max_length": 1024,
"pad_token": "#",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}