7B Fully Open Source Moxin-LLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement

• URL: http://arxiv.org/abs/2412.06845v4
• Date: Wed, 23 Apr 2025 01:38:02 GMT
• Title: 7B Fully Open Source Moxin-LLM -- From Pretraining to GRPO-based Reinforcement Learning Enhancement
• Authors: Pu Zhao, Xuan Shen, Zhenglun Kong, Yixin Shen, Sung-En Chang, Timothy Rupprecht, Lei Lu, Enfu Nan, Changdi Yang, Yumei He, Weiyan Shi, Xingchen Xu, Yu Huang, Wei Jiang, Wei Wang, Yue Chen, Yong He, Yanzhi Wang,
• Abstract summary: Moxin 7B is a fully open-source Large Language Models (LLMs) developed adhering to principles of open science, open source, open data, and open access.<n>We release the pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints.<n> Experiments show that our models achieve superior performance in various evaluations such as zero-shot evaluation, few-shot evaluation, and CoT evaluation.
• Score: 42.10844666788254
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recently, Large Language Models (LLMs) have undergone a significant transformation, marked by a rapid rise in both their popularity and capabilities. Leading this evolution are proprietary LLMs like GPT-4 and GPT-o1, which have captured widespread attention in the AI community due to their remarkable performance and versatility. Simultaneously, open-source LLMs, such as LLaMA, have made great contributions to the ever-increasing popularity of LLMs due to the ease to customize and deploy the models across diverse applications. Although open-source LLMs present unprecedented opportunities for innovation and research, the commercialization of LLMs has raised concerns about transparency, reproducibility, and safety. Many open-source LLMs fail to meet fundamental transparency requirements by withholding essential components like training code and data, which may hinder further innovations on LLMs. To mitigate this issue, we introduce Moxin 7B, a fully open-source LLM developed, adhering to principles of open science, open source, open data, and open access. We release the pre-training code and configurations, training and fine-tuning datasets, and intermediate and final checkpoints, aiming to make continuous commitments to fully open-source LLMs. After pre-training and obtaining the base model, we finetune the Moxin Base model with SOTA post-training framework and instruction data to obtain Moxin Instruct model. To improve the reasoning capability, we further finetune our Instruct model with chain-of-thought data distilled from DeepSeek R1, and then use Group Relative Policy Optimization (GRPO), an efficient and effective reinforcement learning algorithm following DeepSeek R1, to finetune our model, leading to the Moxin Reasoning model. Experiments show that our models achieve superior performance in various evaluations such as zero-shot evaluation, few-shot evaluation, and CoT evaluation.

Related papers

• Federated In-Context LLM Agent Learning [3.4757641432843487]
  Large Language Models (LLMs) have revolutionized intelligent services by enabling logical reasoning, tool use, and interaction with external systems as agents. In this paper, we propose a novel privacy-preserving Federated In-context LLM Agent Learning (FICAL) algorithm. The results show that FICAL has competitive performance compared to other SOTA baselines with a significant communication cost decrease of $mathbf3.33times105$ times.
  arXiv  Detail & Related papers  (2024-12-11T03:00:24Z)
• MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series [86.31735321970481]
  We open-source MAP-Neo, a bilingual language model with 7B parameters trained from scratch on 4.5T high-quality tokens. Our MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2024-05-29T17:57:16Z)
• A Survey on Self-Evolution of Large Language Models [116.54238664264928]
  Large language models (LLMs) have significantly advanced in various fields and intelligent agent applications. To address this issue, self-evolution approaches that enable LLMs to autonomously acquire, refine, and learn from experiences generated by the model itself are rapidly growing.
  arXiv  Detail & Related papers  (2024-04-22T17:43:23Z)
• OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models [44.848642930797155]
  We release OpenMoE, a series of fully open-sourced and reproducible decoder-only Mixture-of-Experts (MoE) based large language models (LLMs) Our investigation confirms that MoE-based LLMs can offer a more favorable cost-effectiveness trade-off than dense LLMs. We find that routing decisions in MoE models are predominantly based on token IDs, with minimal context relevance.
  arXiv  Detail & Related papers  (2024-01-29T12:05:02Z)
• Knowledge Fusion of Large Language Models [73.28202188100646]
  This paper introduces the notion of knowledge fusion for large language models (LLMs) We externalize their collective knowledge and unique strengths, thereby elevating the capabilities of the target model beyond those of any individual source LLM. Our findings confirm that the fusion of LLMs can improve the performance of the target model across a range of capabilities such as reasoning, commonsense, and code generation.
  arXiv  Detail & Related papers  (2024-01-19T05:02:46Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
  Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering. The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored. We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
  arXiv  Detail & Related papers  (2023-12-26T07:24:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.