Initial commit

scratch.py

@@ -0,0 +1,15 @@
+#%%
+
+import json 
+fname = "tokenizer.json"
+
+with open(fname, 'r') as f:
+    vocab = json.load(f)
+
+# %%
+
+# dump this is vocab_2.json
+fname2  = "vocab_2.json"
+with open(fname2, 'w') as f:
+    json.dump(vocab, f)
+# %%

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}, "pad_token": "<|endoftext|>"}

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": "<|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, "padding": "max_length", "model_max_length": 1024, "special_tokens_map_file": null, "tokenizer_file": "/home/jupyter/.cache/huggingface/transformers/16a2f78023c8dc511294f0c97b5e10fde3ef9889ad6d11ffaa2a00714e73926e.cf2d0ecb83b6df91b3dbb53f1d1e4c311578bfd3aa0e04934215a49bf9898df0", "name_or_path": "gpt2_sum_1/checkpoint-1977", "tokenizer_class": "GPT2Tokenizer"}