use_ray: false

model: Qwen/Qwen2.5-VL-3B-Instruct
dataset: modelscope/competition_math#16
num_return_sequences: 4
max_length: 2048
system: "You are a math model, you should **think step by step** carefully, and always consider the basic math principles to avoid making calculating mistakes. Give the final answer wrapped with \\boxed{{}}"
load_args: false
sampler_engine: vllm
max_new_tokens: 768
orm_model: math
prm_model: Qwen/Qwen2.5-Math-PRM-7B
override_exist_file: true
num_sampling_batch_size: 4
top_p: 1.0
temperature: 1.0
prm_threshold: 0.8
output_file: sampling.jsonl

device_groups:
  nproc_per_node: 4
  sample_group:
    device: GPU
    ranks: list(range(0, 2))
    workers:
      - sampler
  rm_group:
    device: GPU
    ranks: list(range(2, 4))
    workers:
      - prm
      - orm