test-test / tokenizer_config.json

Training in progress, step 2

25506a4 about 4 years ago

255 Bytes

{
  "add_prefix_space": false,
  "bos_token": "<|endoftext|>",
  "eos_token": "<|endoftext|>",
  "model_max_length": 1024,
  "name_or_path": "gpt2",
  "special_tokens_map_file": null,
  "tokenizer_class": "GPT2Tokenizer",
  "unk_token": "<|endoftext|>"
}

	{
	"add_prefix_space": false,
	"bos_token": "<\|endoftext\|>",
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 1024,
	"name_or_path": "gpt2",
	"special_tokens_map_file": null,
	"tokenizer_class": "GPT2Tokenizer",
	"unk_token": "<\|endoftext\|>"
	}