regolo/brick-complexity-2-max-Q8_0-GGUF

huggingface-cli download regolo/brick-complexity-2-max-Q8_0-GGUF brick-complexity-2-max-Q8_0.gguf --local-dir ./models

./llama-cli -m ./models/brick-complexity-2-max-Q8_0.gguf \
    -p "<|im_start|>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.<|im_end|>
<|im_start|>user
Classify: What is the capital of France?<|im_end|>
<|im_start|>assistant
" \
    -n 5 --temp 0

cat > Modelfile <<EOF
FROM ./brick-complexity-2-max-Q8_0.gguf

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."""

TEMPLATE """<|im_start|>system
{{ .System }}<|im_end|>
<|im_start|>user
Classify: {{ .Prompt }}<|im_end|>
<|im_start|>assistant
"""

PARAMETER temperature 0
PARAMETER num_predict 5
EOF

ollama create brick-complexity-2-max -f Modelfile
ollama run brick-complexity-2-max "Design a distributed consensus algorithm"
# Output: hard

from vllm import LLM, SamplingParams

llm = LLM(model="regolo/brick-complexity-2-max-Q8_0-GGUF")
sp = SamplingParams(temperature=0, max_tokens=5)

prompt = """<|im_start|>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.<|im_end|>
<|im_start|>user
Classify: Explain the rendering equation from radiometric first principles<|im_end|>
<|im_start|>assistant
"""

out = llm.generate([prompt], sp)
print(out[0].outputs[0].text.strip())
# Output: hard