{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/minicpm-unveiling-the-potential-of-small","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","arxiv_id":"2404.06395","date":"2024-04-09","proceeding":null,"authors":["Shengding Hu","Yuge Tu","Xu Han","Chaoqun He","Ganqu Cui","Xiang Long","Zhi Zheng","Yewei Fang","Yuxiang Huang","Weilin Zhao","Xinrong Zhang","Zheng Leng Thai","Kaihuo Zhang","Chongyi Wang","Yuan YAO","Chenyang Zhao","Jie zhou","Jie Cai","Zhongwu Zhai","Ning Ding","Chao Jia","Guoyang Zeng","Dahai Li","Zhiyuan Liu","Maosong Sun"],"abstract":"The burgeoning interest in developing Large Language Models (LLMs) with up to trillion parameters has been met with concerns regarding resource efficiency and practical expense, particularly given the immense cost of experimentation. This scenario underscores the importance of exploring the potential of Small Language Models (SLMs) as a resource-efficient alternative. In this context, we introduce MiniCPM, specifically the 1.2B and 2.4B non-embedding parameter variants, not only excel in their respective categories but also demonstrate capabilities on par with 7B-13B LLMs. While focusing on SLMs, our approach exhibits scalability in both model and data dimensions for future LLM research. Regarding model scaling, we employ extensive model wind tunnel experiments for stable and optimal scaling. For data scaling, we introduce a Warmup-Stable-Decay (WSD) learning rate scheduler (LRS), conducive to continuous training and domain adaptation. We present an in-depth analysis of the intriguing training dynamics that occurred in the WSD LRS. With WSD LRS, we are now able to efficiently study data-model scaling law without extensive retraining experiments on both axes of model and data, from which we derive the much higher compute optimal data-model ratio than Chinchilla Optimal. Additionally, we introduce MiniCPM family, including MiniCPM-DPO, MiniCPM-MoE and MiniCPM-128K, whose excellent performance further cementing MiniCPM's foundation in diverse SLM applications. MiniCPM models are available publicly at https://github.com/OpenBMB/MiniCPM .","url_abs":"https://arxiv.org/abs/2404.06395v3","url_pdf":"https://arxiv.org/pdf/2404.06395v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"minicpm-unveiling-the-potential-of-small","repo_url":"https://github.com/openbmb/minicpm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"minicpm-unveiling-the-potential-of-small","repo_url":"https://github.com/pwc-1/Paper-5/tree/main/minicpm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"minicpm-unveiling-the-potential-of-small","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/2/minicpm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"}],"methods":[{"method_slug":"chinchilla","method_name":"Chinchilla"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.06395","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.06395"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/2/minicpm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/openbmb/minicpm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-5/tree/main/minicpm","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"8710fdb70fe69494","entry":"reverse_last_round","repo":"openbmb/minicpm","repo_kind":"official","path":"demo/minicpm/hf_based_demo.py","file_url":"https://github.com/openbmb/minicpm/blob/HEAD/demo/minicpm/hf_based_demo.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8710fdb70fe69494"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}