{"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/sphinx-x-scaling-data-and-parameters-for-a","title":"SPHINX-X: Scaling Data and Parameters for a Family of Multi-modal Large Language Models","arxiv_id":"2402.05935","date":"2024-02-08","proceeding":null,"authors":["Dongyang Liu","Renrui Zhang","Longtian Qiu","Siyuan Huang","Weifeng Lin","Shitian Zhao","Shijie Geng","Ziyi Lin","Peng Jin","Kaipeng Zhang","Wenqi Shao","Chao Xu","Conghui He","Junjun He","Hao Shao","Pan Lu","Hongsheng Li","Yu Qiao","Peng Gao"],"abstract":"We propose SPHINX-X, an extensive Multimodality Large Language Model (MLLM) series developed upon SPHINX. To improve the architecture and training efficiency, we modify the SPHINX framework by removing redundant visual encoders, bypassing fully-padded sub-images with skip tokens, and simplifying multi-stage training into a one-stage all-in-one paradigm. To fully unleash the potential of MLLMs, we assemble a comprehensive multi-domain and multimodal dataset covering publicly available resources in language, vision, and vision-language tasks. We further enrich this collection with our curated OCR intensive and Set-of-Mark datasets, extending the diversity and generality. By training over different base LLMs including TinyLlama1.1B, InternLM2-7B, LLaMA2-13B, and Mixtral8x7B, we obtain a spectrum of MLLMs that vary in parameter size and multilingual capabilities. Comprehensive benchmarking reveals a strong correlation between the multi-modal performance with the data and parameter scales. Code and models are released at https://github.com/Alpha-VLLM/LLaMA2-Accessory","url_abs":"https://arxiv.org/abs/2402.05935v2","url_pdf":"https://arxiv.org/pdf/2402.05935v2.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":"sphinx-x-scaling-data-and-parameters-for-a","repo_url":"https://github.com/alpha-vllm/llama2-accessory","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"video-question-answering","task_name":"Video Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-question-answering-on-mvbench","task":"Video Question Answering","dataset":"MVBench","model":"SPHINX-Plus","rank_in_archive_order":15,"of":22,"metrics":{"Avg.":"39.7"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"SPHINX-Plus","rank_in_archive_order":77,"of":231,"metrics":{"GPT-4 score":"47.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2402.05935","atlas_url":"https://app.syntology.ai/?focus=2402.05935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.05935"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/alpha-vllm/llama2-accessory","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"dcae39c8928b5fd8","entry":"apply_rotary_emb","repo":"alpha-vllm/llama2-accessory","repo_kind":"official","path":"accessory/model/LLM/llama.py","file_url":"https://github.com/alpha-vllm/llama2-accessory/blob/HEAD/accessory/model/LLM/llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"dcae39c8928b5fd8"}},{"code_sha256_prefix":"2c4423db8989ee05","entry":"precompute_freqs_cis","repo":"alpha-vllm/llama2-accessory","repo_kind":"official","path":"accessory/model/LLM/llama.py","file_url":"https://github.com/alpha-vllm/llama2-accessory/blob/HEAD/accessory/model/LLM/llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2c4423db8989ee05"}},{"code_sha256_prefix":"70bf6ebaafd266c4","entry":"reshape_for_broadcast","repo":"alpha-vllm/llama2-accessory","repo_kind":"official","path":"accessory/model/LLM/llama.py","file_url":"https://github.com/alpha-vllm/llama2-accessory/blob/HEAD/accessory/model/LLM/llama.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"70bf6ebaafd266c4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}