P-Aligner

Quick Start

from vllm import LLM, SamplingParams
from transformers import AutoTokenizer

raw_instruction = "What is the capital of France?"
model_path = "P-Aligner"

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
model = LLM(
    model=model_path,
    gpu_memory_utilization=0.9,
    enable_prefix_caching=True,
    dtype="bfloat16",
)

outputs = model.generate(
    [raw_instruction],
    sampling_params=SamplingParams(
        temperature=0.0,
        max_tokens=2048,
    ),
)
better_instruction = tokenizer.parse_output(
    outputs[0].outputs[0].text,
    raw_instruction,
)

print(better_instruction)