diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..12aff97 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,6 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "", + "pad_token": "[PAD]" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..89716b4 Binary files /dev/null and b/tokenizer.model differ diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..7890431 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,7 @@ +{ + "bos_token": "", + "eos_token": "", + "model_max_length": 1000000000000000019884624838656, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "" +}