add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<bos>": 50257, "<eos>": 50258, "<sep>": 50259, "<pad>": 50260}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<bos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<eos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "sep_token": "<sep>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<bos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<eos>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "pad_token": "<pad>", "sep_token": "<sep>", "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/root/.cache/huggingface/transformers/16a2f78023c8dc511294f0c97b5e10fde3ef9889ad6d11ffaa2a00714e73926e.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}