add tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<|12space|>": 50258, "<|endofcomment|>": 50267, "<|8space|>": 50265, "<|10space|>": 50257, "<|2space|>": 50262, "<|14space|>": 50259, "<|4space|>": 50263, "<|6space|>": 50264, "<|cell|>": 50266, "<|18space|>": 50261, "<|16space|>": 50260}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}

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, "name_or_path": "/Users/heyman/code/gpt2_medium-pynb_origtok_specialtoks-pynbv5-200k_lr=2e-4", "special_tokens_map_file": "/nfs/datasets/lm4code/tokenizers/gpt2/special_tokens_map.json", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}