add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<|Anirudh H M|>": 50263, "<|Saarthak Agarwal|>": 50265, "<|Vinay Kirpalani|>": 50260, "<|Vishesh P|>": 50258, "<|Aditeya Baral|>": 50257, "<|Soukumarya Saha|>": 50266, "<|Siddharth K Rao|>": 50264, "<|Ansh Sarkar|>": 50261, "<|Aronya Baksy|>": 50259, "<|Arpit Kumar|>": 50262}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "additional_special_tokens": ["<|Aditeya Baral|>", "<|Vishesh P|>", "<|Aronya Baksy|>", "<|Vinay Kirpalani|>", "<|Ansh Sarkar|>", "<|Arpit Kumar|>", "<|Anirudh H M|>", "<|Siddharth K Rao|>", "<|Saarthak Agarwal|>", "<|Soukumarya Saha|>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "model_max_length": 1024, "additional_special_tokens": ["<|Aditeya Baral|>", "<|Vishesh P|>", "<|Aronya Baksy|>", "<|Vinay Kirpalani|>", "<|Ansh Sarkar|>", "<|Arpit Kumar|>", "<|Anirudh H M|>", "<|Siddharth K Rao|>", "<|Saarthak Agarwal|>", "<|Soukumarya Saha|>"], "special_tokens_map_file": null, "name_or_path": "/content/drive/MyDrive/Colab Notebooks/sonobois dialogpt", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}