Add pytorch and tokenizer

added_tokens.json

@@ -0,0 +1 @@
+{"<|endoftext|>": 50257}

jax2torch.py

@@ -0,0 +1,15 @@
+from transformers import AutoTokenizer, GPT2LMHeadModel
+
+'''
+
+This is a script to convert the Jax model and the tokenizer to Pytorch model
+
+'''
+
+model = GPT2LMHeadModel.from_pretrained(".", from_flax=True)
+
+model.save_pretrained(".")
+
+tokenizer = AutoTokenizer.from_pretrained(".")
+
+tokenizer.save_pretrained(".")

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aa8f92e4afdbbb4c26a49803b7db96d7705c9b24d3406ab49fdc3ccfc8b69c7
+size 510401385

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, "special_tokens_map_file": null, "name_or_path": ".", "errors": "replace", "tokenizer_class": "GPT2Tokenizer"}