{"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/simvlm-simple-visual-language-model","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","arxiv_id":"2108.10904","date":"2021-08-24","proceeding":"ICLR 2022 4","authors":["ZiRui Wang","Jiahui Yu","Adams Wei Yu","Zihang Dai","Yulia Tsvetkov","Yuan Cao"],"abstract":"With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations including clean image captions and regional labels limits the scalability of existing approaches, and complicates the pretraining procedure with the introduction of multiple dataset-specific objectives. In this work, we relax these constraints and present a minimalist pretraining framework, named Simple Visual Language Model (SimVLM). Unlike prior work, SimVLM reduces the training complexity by exploiting large-scale weak supervision, and is trained end-to-end with a single prefix language modeling objective. Without utilizing extra data or task-specific customization, the resulting model significantly outperforms previous pretraining methods and achieves new state-of-the-art results on a wide range of discriminative and generative vision-language benchmarks, including VQA (+3.74% vqa-score), NLVR2 (+1.17% accuracy), SNLI-VE (+1.37% accuracy) and image captioning tasks (+10.1% average CIDEr score). Furthermore, we demonstrate that SimVLM acquires strong generalization and transfer ability, enabling zero-shot behavior including open-ended visual question answering and cross-modality transfer.","url_abs":"https://arxiv.org/abs/2108.10904v3","url_pdf":"https://arxiv.org/pdf/2108.10904v3.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":"simvlm-simple-visual-language-model","repo_url":"https://github.com/FerryHuang/SimVLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"simvlm-simple-visual-language-model","repo_url":"https://github.com/yulong-XJTU/SimVLM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"}],"methods":[{"method_slug":"simvlm","method_name":"SimVLM"}],"datasets_introduced":[],"methods_introduced":[{"slug":"simvlm","name":"SimVLM","full_name":"Simple Visual Language Model"}],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"SimVLM","rank_in_archive_order":17,"of":41,"metrics":{"BLEU-4":"40.6","CIDER":"143.3","METEOR":"33.4","SPICE":"25.4"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-entire","task":"Image Captioning","dataset":"nocaps entire","model":"Single Model","rank_in_archive_order":6,"of":39,"metrics":{"B1":"83.78","B2":"68.86","B3":"51.06","B4":"32.2","CIDEr":"110.31","METEOR":"30.55","ROUGE-L":"59.86","SPICE":"14.49"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-in-domain","task":"Image Captioning","dataset":"nocaps in-domain","model":"Single Model","rank_in_archive_order":7,"of":41,"metrics":{"B1":"84.64","B2":"70.0","B3":"52.96","B4":"34.66","CIDEr":"108.98","METEOR":"31.97","ROUGE-L":"61.01","SPICE":"14.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-near-domain","task":"Image Captioning","dataset":"nocaps near-domain","model":"Single Model","rank_in_archive_order":6,"of":40,"metrics":{"B1":"84.36","B2":"69.83","B3":"52.42","B4":"33.74","CIDEr":"110.76","METEOR":"30.97","ROUGE-L":"60.46","SPICE":"14.61"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-out-of-domain","task":"Image Captioning","dataset":"nocaps out-of-domain","model":"Single Model","rank_in_archive_order":6,"of":40,"metrics":{"B1":"80.89","B2":"64.21","B3":"44.38","B4":"24.47","CIDEr":"109.49","METEOR":"27.91","ROUGE-L":"56.69","SPICE":"13.89"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-in-domain","task":"Image Captioning","dataset":"nocaps-val-in-domain","model":"SimVLM","rank_in_archive_order":6,"of":11,"metrics":{"CIDEr":"113.7","Pre-train (#images)":"1.8B","SPICE":"-"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-near-domain","task":"Image Captioning","dataset":"nocaps-val-near-domain","model":"SimVLM","rank_in_archive_order":6,"of":10,"metrics":{"CIDEr":"110.9","Pre-train (#images)":"1.8B","SPICE":"-"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-out-domain","task":"Image Captioning","dataset":"nocaps-val-out-domain","model":"SimVLM","rank_in_archive_order":5,"of":10,"metrics":{"CIDEr":"115.2","Pretrain (#images)":"1.8B","SPICE":"-"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-val-overall","task":"Image Captioning","dataset":"nocaps-val-overall","model":"SimVLM","rank_in_archive_order":6,"of":11,"metrics":{"CIDEr":"112.2","Pretrain (#images)":"1.8B","SPICE":"-"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-test","task":"Visual Entailment","dataset":"SNLI-VE test","model":"SimVLM","rank_in_archive_order":4,"of":8,"metrics":{"Accuracy":"86.32"},"uses_additional_data":false},{"leaderboard":"/sota/visual-entailment-on-snli-ve-val","task":"Visual Entailment","dataset":"SNLI-VE val","model":"SimVLM","rank_in_archive_order":4,"of":9,"metrics":{"Accuracy":"86.21"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-dev","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-dev","model":"SimVLM","rank_in_archive_order":14,"of":56,"metrics":{"Accuracy":"80.03"},"uses_additional_data":false},{"leaderboard":"/sota/visual-question-answering-on-vqa-v2-test-std","task":"Visual Question Answering (VQA)","dataset":"VQA v2 test-std","model":"SimVLM","rank_in_archive_order":6,"of":38,"metrics":{"overall":"80.34"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-dev","task":"Visual Reasoning","dataset":"NLVR2 Dev","model":"SimVLM","rank_in_archive_order":8,"of":15,"metrics":{"Accuracy":"84.53"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-nlvr2-test","task":"Visual Reasoning","dataset":"NLVR2 Test","model":"SimVLM","rank_in_archive_order":7,"of":14,"metrics":{"Accuracy":"85.15"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.10904"}},"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/yulong-XJTU/SimVLM","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/FerryHuang/SimVLM","reach":null}],"summary":{"ran":8,"ran_draft_wrong":5,"ran_honours":1,"ran_violates":3,"ran_fixture":1,"unverified":19},"by_repo_kind":{"listed":{"samples":37,"ran":18,"repositories":2}},"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":28,"samples":[{"code_sha256_prefix":"325812bbd82c157f","entry":"BottleneckBlock","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"325812bbd82c157f"}},{"code_sha256_prefix":"38a875bbe943570b","entry":"CNNBlockBase","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"38a875bbe943570b"}},{"code_sha256_prefix":"15258dcfb20b4488","entry":"Conv2d","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15258dcfb20b4488"}},{"code_sha256_prefix":"af6a9f58115fe4d6","entry":"FrozenBatchNorm2d","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"af6a9f58115fe4d6"}},{"code_sha256_prefix":"1150381a8d9193ec","entry":"SimVLMAttention","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1150381a8d9193ec"}},{"code_sha256_prefix":"7bb4727aca21db84","entry":"SimVLMConfig","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7bb4727aca21db84"}},{"code_sha256_prefix":"71c5d4fa9540b172","entry":"SimVLMEncoder","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"71c5d4fa9540b172"}},{"code_sha256_prefix":"81921e47a333c79d","entry":"SimVLMIntermediate","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"81921e47a333c79d"}},{"code_sha256_prefix":"98f385d847636a3e","entry":"basic_clean","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/tokenizer.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98f385d847636a3e"}},{"code_sha256_prefix":"f6f30fe91451a8e9","entry":"batch_input","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f6f30fe91451a8e9"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"train_simVLM.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/train_simVLM.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"a98857f046bfe3d9","entry":"find_pruneable_heads_and_indices","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a98857f046bfe3d9"}},{"code_sha256_prefix":"32b567f5aaaa591d","entry":"generate_square_subsequent_mask","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/SimVLM.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/SimVLM.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"32b567f5aaaa591d"}},{"code_sha256_prefix":"7934a70c6ec449cd","entry":"get_norm","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7934a70c6ec449cd"}},{"code_sha256_prefix":"cddcbab01417b2c1","entry":"pad_with_id","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cddcbab01417b2c1"}},{"code_sha256_prefix":"52de2aaa15da0643","entry":"prune_linear_layer","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"52de2aaa15da0643"}},{"code_sha256_prefix":"a9e07bbdd8c03e94","entry":"subsequent_mask","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a9e07bbdd8c03e94"}},{"code_sha256_prefix":"9542161e9640b858","entry":"whitespace_clean","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/tokenizer.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/tokenizer.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9542161e9640b858"}},{"code_sha256_prefix":"cb7f9fd225d85d47","entry":"ResBlock","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cb7f9fd225d85d47"}},{"code_sha256_prefix":"0ac4351224f69633","entry":"SimVLMCrossAttention","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ac4351224f69633"}},{"code_sha256_prefix":"e21d8701f32d884a","entry":"SimVLMDecoder","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e21d8701f32d884a"}},{"code_sha256_prefix":"d5689e71173b58c7","entry":"SimVLMDecoderLayer","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d5689e71173b58c7"}},{"code_sha256_prefix":"5e83675c723559e7","entry":"SimVLMEmbeddings","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5e83675c723559e7"}},{"code_sha256_prefix":"6560411928394c1b","entry":"SimVLMEncoderLayer","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6560411928394c1b"}},{"code_sha256_prefix":"aed65580e72ec1ea","entry":"SimVLMModel","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"aed65580e72ec1ea"}},{"code_sha256_prefix":"bf481d655ef58d6c","entry":"SimVLMOutput","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bf481d655ef58d6c"}},{"code_sha256_prefix":"2a710d51d64808b5","entry":"SimVLMPatchEmbeddings","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2a710d51d64808b5"}},{"code_sha256_prefix":"e1e1e84518402f22","entry":"SimVLMSelfAttention","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e1e1e84518402f22"}},{"code_sha256_prefix":"679fbced2dad1b6f","entry":"SimVLMSelfOutput","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"679fbced2dad1b6f"}},{"code_sha256_prefix":"3e24126396b28223","entry":"SimVLMTextEmbeddings","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3e24126396b28223"}},{"code_sha256_prefix":"bd7c399bd6fdf0f2","entry":"SimVLMToLogits","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd7c399bd6fdf0f2"}},{"code_sha256_prefix":"a3a75620f09b426d","entry":"c2_msra_fill","repo":"FerryHuang/SimVLM","repo_kind":"listed","path":"simvlm/modeling_simvlm.py","file_url":"https://github.com/FerryHuang/SimVLM/blob/HEAD/simvlm/modeling_simvlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a3a75620f09b426d"}},{"code_sha256_prefix":"f7592e6aa673ef9a","entry":"clone","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/SimVLM.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/SimVLM.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7592e6aa673ef9a"}},{"code_sha256_prefix":"beb8f635f68b899d","entry":"decoder","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/torch_transformer.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/torch_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"beb8f635f68b899d"}},{"code_sha256_prefix":"053efec6ba1e990f","entry":"encoder","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/torch_transformer.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/torch_transformer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"053efec6ba1e990f"}},{"code_sha256_prefix":"3d914d6f21ea094c","entry":"get_norm","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/resblock.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/resblock.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3d914d6f21ea094c"}},{"code_sha256_prefix":"b50994ad24f6d583","entry":"get_pairs","repo":"yulong-XJTU/SimVLM","repo_kind":"listed","path":"model/tokenizer.py","file_url":"https://github.com/yulong-XJTU/SimVLM/blob/HEAD/model/tokenizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b50994ad24f6d583"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}