R-08-Transformer-Baseline / tokenizer_config.json

Sync corrected public source from GitHub (2026-11-07)

f011463 verified 3 days ago

219 Bytes

{
  "model_type": "gpt2",
  "tokenizer_class": "PreTrainedTokenizerFast",
  "bos_token": "<|bos|>",
  "eos_token": "<|eos|>",
  "unk_token": "<|unk|>",
  "pad_token": "<|pad|>",
  "clean_up_tokenization_spaces": false
}

	{
	"model_type": "gpt2",
	"tokenizer_class": "PreTrainedTokenizerFast",
	"bos_token": "<\|bos\|>",
	"eos_token": "<\|eos\|>",
	"unk_token": "<\|unk\|>",
	"pad_token": "<\|pad\|>",
	"clean_up_tokenization_spaces": false
	}