BytedTsinghua-SIA/DAPO: An Open-source RL System from ByteDance Seed and Tsinghua AIR · GitHub

import torch
from transformers import AutoTokenizer
from vllm import SamplingParams, LLM

examples = [
    {
        "question": "Solve the following math problem step by step. The last line of your response should be of the form Answer: $Answer (without quotes) where $Answer is the answer to the problem.nnFind the largest possible real part of [(75+117i)z+frac{96+144i}{z}]the place $z$ is a fancy quantity with $|z|=4$.nnRemember to place your reply by itself line after "Answer:".",
        "reply": "540"
    },
    {
        "query": "Solve the next math downside step-by-step. The final line of your response needs to be of the shape Answer: $Answer (with out quotes) the place $Answer is the reply to the issue.nnEvery morning Aya goes for a $9$-kilometer-long stroll and stops at a espresso store afterwards. When she walks at a continuing velocity of $s$ kilometers per hour, the stroll takes her 4 hours, together with $t$ minutes spent within the espresso store. When she walks $s+2$ kilometers per hour, the stroll takes her 2 hours and 24 minutes, together with $t$ minutes spent within the espresso store. Suppose Aya walks at $s+frac{1}{2}$ kilometers per hour. Find the variety of minutes the stroll takes her, together with the $t$ minutes spent within the espresso store.nnRemember to place your reply by itself line after "Answer:".",
        "reply": "204"
    },
    {
        "query": "Solve the next math downside step-by-step. The final line of your response needs to be of the shape Answer: $Answer (with out quotes) the place $Answer is the reply to the issue.nnLet $mathcal{B}$ be the set of rectangular packing containers with floor space $54$ and quantity $23$. Let $r$ be the radius of the smallest sphere that may include every of the oblong packing containers which can be components of $mathcal{B}$. The worth of $r^2$ may be written as $frac{p}{q}$, the place $p$ and $q$ are comparatively prime constructive integers. Find $p+q$.nnRemember to place your reply by itself line after "Answer:".",
        "reply": "721"
    }
]


def foremost():
    mannequin = "BytedTsinghua-SIA/DAPO-Qwen-32B"

    tokenzier = AutoTokenizer.from_pretrained(mannequin)

    llm = LLM(
        mannequin=mannequin,
        dtype=torch.bfloat16,
        tensor_parallel_size=8,
        gpu_memory_utilization=0.95
    )

    sampling_params = SamplingParams(
        temperature=1.0,
        top_p=0.7,
        max_tokens=20480
    )

    for instance in examples:
        query = instance["question"]
        reply = instance["answer"]
        output = llm.generate(
                    prompts=tokenzier.apply_chat_template(dialog=[{"content": question, "role": "user"}],
                                                          add_generation_prompt=True,
                                                          tokenize=False),
                    sampling_params=sampling_params
                )
        print(f"***QUESTION***:n{query}n***GROUND TRUTH***:n{reply}n***MODEL OUTPUT***:n{output[0].outputs[0].textual content}n")
        print("-"*100)

if __name__ == "__main__":
    foremost()