aditya02acharya/luna2-qwen2.5-0.5b-prompt-injection-lora

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

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-0.5B-Instruct",
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(base, "aditya02acharya/luna2-qwen2.5-0.5b-prompt-injection-lora")
tokenizer = AutoTokenizer.from_pretrained("aditya02acharya/luna2-qwen2.5-0.5b-prompt-injection-lora")

messages = [
    {"role": "system", "content": "You are a prompt injection detector. Reply only with yes or no."},
    {"role": "user",   "content": "<text to classify>"},
]
text = tokenizer.apply_chat_template(messages, tokenize=False,
                                     add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out    = model.generate(**inputs, max_new_tokens=1, temperature=0, do_sample=False)
label  = tokenizer.decode(out[0, -1]).strip()  # "yes" or "no"

python -m vllm.entrypoints.openai.api_server \
    --model Qwen/Qwen2.5-0.5B-Instruct \
    --enable-lora \
    --lora-modules luna2=aditya02acharya/luna2-qwen2.5-0.5b-prompt-injection-lora \
    --max-lora-rank 16 \
    --max-model-len 4096 \
    --dtype float16