Fix HuggingFace cache path resolution on Windows

code-analysis/baselines/utils/preprocessing.py

@@ -13,7 +13,8 @@ def preprocess_and_save(args):
 
 
 
-    cache_dir = args.cache_dir
+    # Expand ~ and convert to absolute path to avoid Windows symlink issues
+    cache_dir = os.path.abspath(os.path.expanduser(args.cache_dir))
     os.environ["XDG_CACHE_HOME"] = cache_dir
     if not os.path.exists(cache_dir):
         os.makedirs(cache_dir)

code-detection/baselines/utils/preprocessing.py

@@ -13,7 +13,8 @@ def preprocess_and_save(args):
 
 
 
-    cache_dir = args.cache_dir
+    # Expand ~ and convert to absolute path to avoid Windows symlink issues
+    cache_dir = os.path.abspath(os.path.expanduser(args.cache_dir))
     os.environ["XDG_CACHE_HOME"] = cache_dir
     if not os.path.exists(cache_dir):
         os.makedirs(cache_dir)

requirements.txt

@@ -1,26 +1,35 @@
 # Core deep learning and AI libraries
-torch
-transformers
-accelerate
-datasets
-openai
+torch>=2.0.0
+transformers>=4.30.0
+accelerate>=0.20.0
+datasets>=2.12.0
+openai>=0.27.0
+
+# HuggingFace ecosystem
+huggingface-hub>=0.15.0
+sentencepiece>=0.1.99
+protobuf>=3.20.0
+safetensors>=0.3.0
 
 # Scientific computing
-numpy
-scipy
-scikit-learn
+numpy>=1.24.0
+scipy>=1.10.0
+scikit-learn>=1.2.0
 
 # Data processing and analysis
-pandas
-matplotlib
-seaborn
+pandas>=2.0.0
+matplotlib>=3.7.0
+seaborn>=0.12.0
 
 # Progress bars and logging
-tqdm
-loguru
+tqdm>=4.65.0
+loguru>=0.7.0
 
 # Code parsing
-tree-sitter
+tree-sitter>=0.20.0
 
 # Web requests (for API calls)
-requests
+requests>=2.28.0
+
+# Table formatting
+prettytable>=3.7.0