from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ash256/qwen3-4b-question-gen")
tokenizer = AutoTokenizer.from_pretrained("ash256/qwen3-4b-question-gen")

prompt = "Generate a technical screening question for a senior backend engineer:"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Or with vLLM for faster inference:

python

from vllm import LLM, SamplingParams

llm = LLM(model="ash256/qwen3-4b-question-gen")
outputs = llm.generate(["Generate a technical screening question for a senior backend engineer:"], SamplingParams(max_tokens=256))
print(outputs[0].outputs[0].text)