changes

app/main.py

@@ -4,7 +4,7 @@ from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-# Set Hugging Face cache directory (to avoid permission issues in Docker)
+# Set Hugging Face cache directory to avoid permission issues in Docker
 os.environ["HF_HOME"] = "/app/huggingface_cache"
 os.environ["TRANSFORMERS_CACHE"] = "/app/huggingface_cache"
 
@@ -23,7 +23,7 @@ model = AutoModelForCausalLM.from_pretrained(
     model_name,
     trust_remote_code=True,
     torch_dtype=torch.float32,  # Use float32 for CPU
-    device_map="cpu"  # Force CPU
+    device_map={"": "cpu"}  # Ensure CPU usage
 )
 
 @app.get("/")

requirements.txt

@@ -3,4 +3,3 @@ uvicorn
 torch
 transformers
 accelerate
-bitsandbytes