import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name_or_path = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
device = torch.accelerator.current_accelerator() if torch.accelerator.is_available() else "cpu"

model = AutoModelForCausalLM.from_pretrained(model_name_or_path).to(device)
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)

inputs = tokenizer.encode("This movie was really", return_tensors="pt").to(device)
outputs = model.generate(inputs)
print(tokenizer.decode(outputs[0]))

from transformers import pipeline

model_name_or_path = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
pipe = pipeline("text-generation", model=model_name_or_path)
print(pipe("This movie was really")[0]["generated_text"])

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

base_model_name = "Qwen/Qwen3-0.6B" #path/to/your/model/or/name/on/hub
adapter_model_name = "path/to/my/adapter"

model = AutoModelForCausalLM.from_pretrained(base_model_name)
model = PeftModel.from_pretrained(model, adapter_model_name)

tokenizer = AutoTokenizer.from_pretrained(base_model_name)

model = AutoModelForCausalLM.from_pretrained(base_model_name)
model = PeftModel.from_pretrained(model, adapter_model_name)

model = model.merge_and_unload()
model.save_pretrained("merged_adapters")