Qwen3-4B-Instruct-2507-self-verify-lora

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")
model = PeftModel.from_pretrained(base_model, "codelion/Qwen3-4B-Instruct-2507-self-verify-lora")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-4B-Instruct-2507")

prompt = """<start_of_turn>user
<problem>
Given a number n, return the sum of all numbers from 1 to n.
</problem>

Solve this problem. Show your reasoning in <think> tags, verify your solution, then provide the final code.<end_of_turn>
<start_of_turn>model
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=1024)
print(tokenizer.decode(outputs[0]))