README.md

metadata

license: mit
datasets:
  - sxiong/SWAP_v2
language:
  - en
base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct

Model Card for SWAP_LLM_v2

SWAP_LLM_v2 is a suite of supervised fine-tuned models developed for multi-step reasoning with large language models (LLMs). The framework encompasses two primary components: generator and discriminator.

Model Details

Generator

• Base Model: meta-llama/Meta-Llama-3-8B-Instruct

• LoRA Configuration:

  • lora_alpha: 32
  • r: 16
  • target_modules: ["up_proj", "down_proj", "gate_proj", "q_proj","k_proj", "v_proj", "o_proj"]
  • bias: "none"

For additional information and implementation details, please refer to the SWAP GitHub repository.

Citation

@inproceedings{xiong-etal-2025-deliberate,
    title = "Deliberate Reasoning in Language Models as Structure-Aware Planning with an Accurate World Model",
    author = "Xiong, Siheng  and
      Payani, Ali  and
      Yang, Yuan  and
      Fekri, Faramarz",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.acl-long.1540/",
    doi = "10.18653/v1/2025.acl-long.1540",
    pages = "31900--31931",
    ISBN = "979-8-89176-251-0"
}