scholarly-code-tokenizer / tokenizer_config.json

Publish 18 measured scholarly/code BPE tokenizers and research report

6bbbc6f verified 11 days ago

316 Bytes

{
  "tokenizer_class": "PreTrainedTokenizerFast",
  "clean_up_tokenization_spaces": false,
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "add_bos_token": false,
  "add_eos_token": false,
  "pad_token": "<|pad|>",
  "bos_token": "<|bos|>",
  "eos_token": "<|eos|>",
  "unk_token": "<|unk|>"
}

	{
	"tokenizer_class": "PreTrainedTokenizerFast",
	"clean_up_tokenization_spaces": false,
	"model_input_names": [
	"input_ids",
	"attention_mask"
	],
	"add_bos_token": false,
	"add_eos_token": false,
	"pad_token": "<\|pad\|>",
	"bos_token": "<\|bos\|>",
	"eos_token": "<\|eos\|>",
	"unk_token": "<\|unk\|>"
	}