TinyLinuxDSLM81M_EXTFULL_Instruct / tokenizer_config.json
nagrajn's picture
Upload tokenizer
2fdeaeb verified
raw
history blame
1.37 kB
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50257": {
"content": "[context]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50258": {
"content": "[user]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50259": {
"content": "[assist]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"50260": {
"content": "[fin]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[context]",
"[user]",
"[assist]",
"[fin]"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"max_length": 1024,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "GPT2Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<|endoftext|>"
}