tokenizer_config.json

{
 "add_prefix_space": false,
 "added_tokens_decoder": {
 "50256": {
 "content": "<|endoftext|>",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "50257": {
 "content": "[PAD]",
 "lstrip": false,
 "normalized": false,
 "rstrip": false,
 "single_word": false,
 "special": true
 },
 "50258": {
 "content": "<|im_start|>system",
 "lstrip": false,
 "normalized": true,
 "rstrip": false,
 "single_word": false,
 "special": false
 },
 "50259": {
 "content": "<|im_start|>user",
 "lstrip": false,
 "normalized": true,
 "rstrip": false,
 "single_word": false,
 "special": false
 },
 "50260": {
 "content": "<|im_start|>assistant",
 "lstrip": false,
 "normalized": true,
 "rstrip": false,
 "single_word": false,
 "special": false
 }
 },
 "bos_token": "<|endoftext|>",
 "clean_up_tokenization_spaces": true,
 "eos_token": "<|im_end|>",
 "model_max_length": 500,
 "pad_token": "[PAD]",
 "tokenizer_class": "GPT2Tokenizer",
 "unk_token": "<|endoftext|>"
}