First commit

Dockerfile

@@ -6,4 +6,8 @@ RUN pip install --no-cache-dir -r requirements.txt
 
 COPY . .
 
+mkdir -p /tmp/huggingface
+chmod -R 777 /tmp/huggingface
+
+
 CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -1,13 +1,15 @@
 import os
+
+# Set a writable cache directory
+os.environ["HF_HOME"] = "/tmp/huggingface"
+os.environ["TRANSFORMERS_CACHE"] = "/tmp/huggingface"
+
+# Now import the required libraries
 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"