codegen-350M-mono-java / tokenizer_config.json

Upload tokenizer

b8b2639 almost 3 years ago

237 Bytes

{
  "add_prefix_space": false,
  "bos_token": "<|endoftext|>",
  "clean_up_tokenization_spaces": true,
  "eos_token": "<|endoftext|>",
  "model_max_length": 2048,
  "tokenizer_class": "CodeGenTokenizer",
  "unk_token": "<|endoftext|>"
}

	{
	"add_prefix_space": false,
	"bos_token": "<\|endoftext\|>",
	"clean_up_tokenization_spaces": true,
	"eos_token": "<\|endoftext\|>",
	"model_max_length": 2048,
	"tokenizer_class": "CodeGenTokenizer",
	"unk_token": "<\|endoftext\|>"
	}