First commit

app.py

@@ -1,8 +1,13 @@
+import os
 import torch
 from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
 
+# Set custom cache directory
+os.environ["HF_HOME"] = "/tmp/huggingface"
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface"
+
 # Model setup
 MODEL_NAME = "deepseek-ai/deepseek-llm-7b-base"
 DEVICE = "cuda" if torch.cuda.is_available() else "cpu"