Resolving the files loading issues

Dockerfile

@@ -19,7 +19,7 @@ RUN pip install --no-cache-dir --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt
 
 # Set environment variable for Hugging Face cache
-ENV TRANSFORMERS_CACHE=/app/cache
+ENV HF_HOME=/app/cache
 
 # Create the cache directory with proper permissions
 RUN mkdir -p /app/cache && chmod 777 /app/cache

app.py

@@ -5,6 +5,9 @@ from transformers import AutoTokenizer
 from peft import AutoPeftModelForCausalLM
 import torch
 from typing import Optional
+import os
+
+os.environ['HF_HOME'] = '/app/cache'
 
 app = FastAPI(title="Gemma Script Generator API")
 
@@ -20,6 +23,7 @@ try:
         MODEL_NAME,
         device_map="auto",  # Will use CPU if GPU not available
         trust_remote_code=True,
+        cache_dir = '/app/cache'
         #load_in_4bit=True
     )
 except Exception as e: