Create app.py

app.py

@@ -0,0 +1,23 @@
+from fastapi import FastAPI
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+app = FastAPI()
+
+# Load the LoRA model (4-bit Quantized)
+model_name = "/app/model"  # Local model path
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, torch_dtype=torch.float16, device_map="auto"
+)
+
+@app.post("/generate")
+async def generate_text(prompt: str, max_tokens: int = 50):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, max_new_tokens=max_tokens)
+    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": response}
+
+@app.get("/")
+async def root():
+    return {"message": "Counseling AI Model is Running!"}