regolo/brick-complexity-2-eco

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

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-0.8B", torch_dtype=torch.bfloat16)
tok = AutoTokenizer.from_pretrained("Qwen/Qwen3.5-0.8B")
model = PeftModel.from_pretrained(base, "regolo/brick-complexity-2-eco").eval()

system = """You are a query difficulty classifier for an LLM routing system.
Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
Respond with ONLY one word: easy, medium, or hard."""
prompt = f"<|im_start|>system\n{system}<|im_end|>\n<|im_start|>user\nClassify: Design a distributed consensus algorithm<|im_end|>\n<|im_start|>assistant\n"
ids = tok(prompt, return_tensors="pt").input_ids
out = model.generate(ids, max_new_tokens=3, do_sample=False)
print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True).strip())
# Output: hard

from vllm import LLM, SamplingParams
from vllm.lora.request import LoRARequest

llm = LLM(
    model="Qwen/Qwen3.5-0.8B",
    enable_lora=True,
    max_lora_rank=32,
    dtype="bfloat16",
)
sp = SamplingParams(temperature=0, max_tokens=3)

system = """You are a query difficulty classifier for an LLM routing system.
Classify each query as easy, medium, or hard based on the cognitive depth and domain expertise required to answer correctly.
Respond with ONLY one word: easy, medium, or hard."""
prompt = f"<|im_start|>system\n{system}<|im_end|>\n<|im_start|>user\nClassify: Explain the rendering equation from radiometric first principles<|im_end|>\n<|im_start|>assistant\n"

out = llm.generate(
    [prompt],
    sp,
    lora_request=LoRARequest("brick-complexity-2-eco", 1, "regolo/brick-complexity-2-eco"),
)
print(out[0].outputs[0].text.strip())
# Output: hard