{"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/tinyllava-a-framework-of-small-scale-large","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","arxiv_id":"2402.14289","date":"2024-02-22","proceeding":null,"authors":["Baichuan Zhou","Ying Hu","Xi Weng","Junlong Jia","Jie Luo","Xien Liu","Ji Wu","Lei Huang"],"abstract":"We present the TinyLLaVA framework that provides a unified perspective in designing and analyzing the small-scale Large Multimodal Models (LMMs). We empirically study the effects of different vision encoders, connection modules, language models, training data and training recipes. Our extensive experiments showed that better quality of data combined with better training recipes, smaller LMMs can consistently achieve on-par performances compared to bigger LMMs. Under our framework, we train a family of small-scale LMMs. Our best model, TinyLLaVA-3.1B, achieves better overall performance against existing 7B models such as LLaVA-1.5 and Qwen-VL. We hope our findings can serve as baselines for future research in terms of data scaling, training setups and model selections. Our model weights and codes will be made public.","url_abs":"https://arxiv.org/abs/2402.14289v1","url_pdf":"https://arxiv.org/pdf/2402.14289v1.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":"tinyllava-a-framework-of-small-scale-large","repo_url":"https://github.com/dlcv-buaa/tinyllavabench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"tinyllava-a-framework-of-small-scale-large","repo_url":"https://github.com/tinyllava/tinyllava_factory","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-question-answering-on-mm-vet","task":"Visual Question Answering","dataset":"MM-Vet","model":"TinyLLaVA-share-Sig-Ph","rank_in_archive_order":188,"of":231,"metrics":{"GPT-4 score":"32.0","Params":"3.1B"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2402.14289","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.14289"}},"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/tinyllava/tinyllava_factory","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dlcv-buaa/tinyllavabench","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":4,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":10,"ran":5,"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":"20e4f665698a3d18","entry":"collate_fn","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/eval/model_vqa_loader.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/eval/model_vqa_loader.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"20e4f665698a3d18"}},{"code_sha256_prefix":"42a46570620cd9fa","entry":"get_chunk","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/eval/model_vqa.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42a46570620cd9fa"}},{"code_sha256_prefix":"c2cb10d944648763","entry":"get_value_from_kwargs","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/modeling_tinyllava.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/modeling_tinyllava.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c2cb10d944648763"}},{"code_sha256_prefix":"f0a5e0f0713718b3","entry":"load_pretrained_model","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/load_model.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/load_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f0a5e0f0713718b3"}},{"code_sha256_prefix":"076c252c52cbb161","entry":"split_list","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/eval/model_vqa.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/eval/model_vqa.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"076c252c52cbb161"}},{"code_sha256_prefix":"2a36b652e10f69fa","entry":"convert_legecy_config_to_tinyllavaconfig","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2a36b652e10f69fa"}},{"code_sha256_prefix":"909c4c1d00783db8","entry":"convert_legecy_weights_to_tinyllavafactory","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"909c4c1d00783db8"}},{"code_sha256_prefix":"a351ee8258c5cd44","entry":"convert_state_dict_to_tinyllavafactory","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/convert_legecy_weights_to_tinyllavafactory.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a351ee8258c5cd44"}},{"code_sha256_prefix":"391fc0746cff81a2","entry":"load_base_ckp_for_lora","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/model/load_model.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/model/load_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"391fc0746cff81a2"}},{"code_sha256_prefix":"f3018307f9301da1","entry":"parse_multi_choice_response","repo":"dlcv-buaa/tinyllavabench","repo_kind":"official","path":"tinyllava/eval/model_vqa_mmmu.py","file_url":"https://github.com/dlcv-buaa/tinyllavabench/blob/HEAD/tinyllava/eval/model_vqa_mmmu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f3018307f9301da1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}