ask_datasensei.py

with open("ask_datasensei.py", "w") as f:
    f.write("""
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_name = "microsoft/phi-2"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    trust_remote_code=True
)

# Move model to device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def format_prompt(user_input):
    return f"You are DataSensei 🌸, an anime-style mentor.\nUser: {user_input}\nDataSensei:"

def ask_datasensei(user_input):
    prompt = format_prompt(user_input)
    inputs = tokenizer(prompt, return_tensors="pt").to(device)
    outputs = model.generate(
        **inputs,
        max_new_tokens=1024,
        pad_token_id=tokenizer.eos_token_id,
        do_sample=True,
        temperature=0.7,
        top_p=0.9
    )
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response.split("DataSensei:")[-1].strip()
""")