initialize project structure with Dockerfile, app.py, and requirements.txt

Dockerfile

@@ -0,0 +1,13 @@
+FROM python:3.10
+
+WORKDIR /code
+
+COPY requirements.txt .
+
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 7860
+
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,25 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+app = FastAPI()
+
+class PromptRequest(BaseModel):
+    prompt: str
+
+# Load small LLaMA 3.2B model (or any other compatible)
+MODEL_NAME = "TheBloke/Llama-3-OpenOrca-2.2B-GGUF"
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(MODEL_NAME)
+
+@app.get("/")
+def root():
+    return {"message": "LLaMA 3.2B API for QuizForge is live!"}
+
+@app.post("/generate")
+def generate_text(data: PromptRequest):
+    inputs = tokenizer(data.prompt, return_tensors="pt")
+    outputs = model.generate(**inputs, max_new_tokens=1024)
+    output_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+    return {"response": output_text}

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+transformers
+torch