from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base_model = AutoModelForCausalLM.from_pretrained(
    "google/gemma-3-1b-it",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

model = PeftModel.from_pretrained(
    base_model,
    "zoeeyys/gemma-3-1b-coachfinetuned-v0"
)

tokenizer = AutoTokenizer.from_pretrained(
    "google/gemma-3-1b-it",
    padding_side="left"
)

messages = [
    {"role": "user", "content": "Hi! I want to plan my life."}
]

inputs = tokenizer.apply_chat_template(
    messages,
    add_generation_prompt=True,
    tokenize=True,
    return_dict=True,
    return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=128)

print(
    tokenizer.decode(
        outputs[0][inputs["input_ids"].shape[-1]:],
        skip_special_tokens=True
    )
)