Update tokenization_phi3_small.py (#29)

- Update tokenization_phi3_small.py (71140198d3f643b6c90697e242e537051091c819)


Co-authored-by: Xiren Zhou <[email protected]>

tokenization_phi3_small.py

@@ -5,6 +5,7 @@ from typing import Collection, List, Optional, Dict, Set, Tuple, Union
 from functools import cached_property
 
 import base64
+import requests
 
 from transformers import PreTrainedTokenizer, AddedToken, AutoConfig
 from transformers.models.auto.tokenization_auto import get_tokenizer_config
@@ -102,7 +103,31 @@ class Phi3SmallTokenizer(PreTrainedTokenizer):
         super().__init__(**kwargs)
         self.errors = errors
 
-        base = tiktoken.get_encoding("cl100k_base")
+        try:
+            base = tiktoken.get_encoding("cl100k_base")
+        # This deals with the scenario where user has restricted internet access 
+        # and thus fails to download the tokenizer file from https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken
+        # It is assumed that user should be able to access files on huggingface hub.
+        except requests.RequestException:
+            import hashlib
+            from transformers.utils import cached_file
+            cached_tokenizer_path = cached_file(
+                    "microsoft/Phi-3-small-8k-instruct",
+                    "cl100k_base.tiktoken",
+                    _raise_exceptions_for_gated_repo=False,
+                    _raise_exceptions_for_missing_entries=False,
+                    _raise_exceptions_for_connection_errors=False
+                )
+            tiktoken_cache_dir = os.path.dirname(cached_tokenizer_path)
+            tiktoken_cache_path = os.path.join(
+                tiktoken_cache_dir, 
+                hashlib.sha1("https://openaipublic.blob.core.windows.net/encodings/cl100k_base.tiktoken".encode()).hexdigest()
+            )
+            if not os.path.exists(tiktoken_cache_path):
+                os.rename(cached_tokenizer_path, tiktoken_cache_path)
+            os.environ["TIKTOKEN_CACHE_DIR"] = tiktoken_cache_dir
+            base = tiktoken.get_encoding("cl100k_base")
+            
         if vocab_file is None:
             self.mergeable_ranks: Dict[bytes, int] = base._mergeable_ranks
         else: