{"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/git-a-generative-image-to-text-transformer","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","arxiv_id":"2205.14100","date":"2022-05-27","proceeding":null,"authors":["JianFeng Wang","Zhengyuan Yang","Xiaowei Hu","Linjie Li","Kevin Lin","Zhe Gan","Zicheng Liu","Ce Liu","Lijuan Wang"],"abstract":"In this paper, we design and train a Generative Image-to-text Transformer, GIT, to unify vision-language tasks such as image/video captioning and question answering. While generative models provide a consistent network architecture between pre-training and fine-tuning, existing work typically contains complex structures (uni/multi-modal encoder/decoder) and depends on external modules such as object detectors/taggers and optical character recognition (OCR). In GIT, we simplify the architecture as one image encoder and one text decoder under a single language modeling task. We also scale up the pre-training data and the model size to boost the model performance. Without bells and whistles, our GIT establishes new state of the arts on 12 challenging benchmarks with a large margin. For instance, our model surpasses the human performance for the first time on TextCaps (138.2 vs. 125.5 in CIDEr). Furthermore, we present a new scheme of generation-based image classification and scene text recognition, achieving decent performance on standard benchmarks. Codes are released at \\url{https://github.com/microsoft/GenerativeImage2Text}.","url_abs":"https://arxiv.org/abs/2205.14100v5","url_pdf":"https://arxiv.org/pdf/2205.14100v5.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":"git-a-generative-image-to-text-transformer","repo_url":"https://github.com/microsoft/GenerativeImage2Text","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-captioning","task_name":"Image Captioning"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-to-text","task_name":"Image to text"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"video-captioning","task_name":"Video Captioning"},{"task_slug":"visual-question-answering","task_name":"Visual Question Answering (VQA)"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-captioning-on-coco-captions","task":"Image Captioning","dataset":"COCO Captions","model":"GIT","rank_in_archive_order":3,"of":41,"metrics":{"BLEU-4":"44.1","CIDER":"151.1","METEOR":" 32.2","SPICE":"26.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-entire","task":"Image Captioning","dataset":"nocaps entire","model":"GIT, Single Model","rank_in_archive_order":2,"of":39,"metrics":{"B1":"88.1","B2":"74.81","B3":"57.68","B4":"37.35","CIDEr":"123.39","METEOR":"32.5","ROUGE-L":"63.12","SPICE":"15.94"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-in-domain","task":"Image Captioning","dataset":"nocaps in-domain","model":"GIT2, Single Model","rank_in_archive_order":2,"of":41,"metrics":{"B1":"88.86","B2":"75.86","B3":"59.94","B4":"41.1","CIDEr":"124.18","METEOR":"33.83","ROUGE-L":"63.82","SPICE":"16.36"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-in-domain","task":"Image Captioning","dataset":"nocaps in-domain","model":"GIT, Single Model","rank_in_archive_order":3,"of":41,"metrics":{"B1":"88.55","B2":"76.1","B3":"60.53","B4":"41.65","CIDEr":"122.4","METEOR":"33.41","ROUGE-L":"64.02","SPICE":"16.18"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-near-domain","task":"Image Captioning","dataset":"nocaps near-domain","model":"GIT2, Single Model","rank_in_archive_order":1,"of":40,"metrics":{"B1":"88.9","B2":"75.86","B3":"58.9","B4":"38.95","CIDEr":"125.51","METEOR":"32.95","ROUGE-L":"63.66","SPICE":"16.11"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-near-domain","task":"Image Captioning","dataset":"nocaps near-domain","model":"GIT, Single Model","rank_in_archive_order":3,"of":40,"metrics":{"B1":"88.56","B2":"75.48","B3":"58.46","B4":"38.44","CIDEr":"123.92","METEOR":"32.86","ROUGE-L":"63.5","SPICE":"15.96"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-out-of-domain","task":"Image Captioning","dataset":"nocaps out-of-domain","model":"GIT2, Single Model","rank_in_archive_order":2,"of":40,"metrics":{"B1":"86.28","B2":"71.15","B3":"52.36","B4":"30.15","CIDEr":"122.27","METEOR":"30.15","ROUGE-L":"60.91","SPICE":"15.62"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-out-of-domain","task":"Image Captioning","dataset":"nocaps out-of-domain","model":"GIT, Single Model","rank_in_archive_order":3,"of":40,"metrics":{"B1":"85.99","B2":"71.28","B3":"52.66","B4":"30.04","CIDEr":"122.04","METEOR":"30.45","ROUGE-L":"60.96","SPICE":"15.7"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-entire","task":"Image Captioning","dataset":"nocaps-XD entire","model":"GIT2","rank_in_archive_order":1,"of":12,"metrics":{"B1":"88.43","B2":"75.02","B3":"57.87","B4":"37.65","CIDEr":"124.77","METEOR":"32.56","ROUGE-L":"63.19","SPICE":"16.06"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-entire","task":"Image Captioning","dataset":"nocaps-XD entire","model":"GIT","rank_in_archive_order":2,"of":12,"metrics":{"B1":"88.1","B2":"74.81","B3":"57.68","B4":"37.35","CIDEr":"123.39","METEOR":"32.5","ROUGE-L":"63.12","SPICE":"15.94"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-in-domain","task":"Image Captioning","dataset":"nocaps-XD in-domain","model":"GIT2","rank_in_archive_order":1,"of":11,"metrics":{"B1":"88.86","B2":"75.86","B3":"59.94","B4":"41.1","CIDEr":"124.18","METEOR":"33.83","ROUGE-L":"63.82","SPICE":"16.36"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-in-domain","task":"Image Captioning","dataset":"nocaps-XD in-domain","model":"GIT","rank_in_archive_order":2,"of":11,"metrics":{"B1":"88.55","B2":"76.1","B3":"60.53","B4":"41.65","CIDEr":"122.4","METEOR":"33.41","ROUGE-L":"64.02","SPICE":"16.18"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-near-domain","task":"Image Captioning","dataset":"nocaps-XD near-domain","model":"GIT2","rank_in_archive_order":1,"of":11,"metrics":{"B1":"88.9","B2":"75.86","B3":"58.9","B4":"38.95","CIDEr":"125.51","METEOR":"32.95","ROUGE-L":"63.66","SPICE":"16.11"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-near-domain","task":"Image Captioning","dataset":"nocaps-XD near-domain","model":"GIT","rank_in_archive_order":2,"of":11,"metrics":{"B1":"88.56","B2":"75.48","B3":"58.46","B4":"38.44","CIDEr":"123.92","METEOR":"32.86","ROUGE-L":"63.5","SPICE":"15.96"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-out-of-domain","task":"Image Captioning","dataset":"nocaps-XD out-of-domain","model":"GIT2","rank_in_archive_order":1,"of":11,"metrics":{"B1":"86.28","B2":"71.15","B3":"52.36","B4":"30.15","CIDEr":"122.27","METEOR":"30.15","ROUGE-L":"60.91","SPICE":"15.62"},"uses_additional_data":false},{"leaderboard":"/sota/image-captioning-on-nocaps-xd-out-of-domain","task":"Image Captioning","dataset":"nocaps-XD out-of-domain","model":"GIT","rank_in_archive_order":2,"of":11,"metrics":{"B1":"85.99","B2":"71.28","B3":"52.66","B4":"30.04","CIDEr":"122.04","METEOR":"30.45","ROUGE-L":"60.96","SPICE":"15.7"},"uses_additional_data":false},{"leaderboard":"/sota/video-captioning-on-msr-vtt-1","task":"Video Captioning","dataset":"MSR-VTT","model":"GIT2","rank_in_archive_order":3,"of":24,"metrics":{"BLEU-4":"54.8","CIDEr":"75.9","GS":"201.6","METEOR":"33.1","ROUGE-L":"68.2"},"uses_additional_data":true},{"leaderboard":"/sota/visual-question-answering-on-msvd-qa-1","task":"Visual Question Answering (VQA)","dataset":"MSVD-QA","model":"GIT","rank_in_archive_order":9,"of":36,"metrics":{"Accuracy":"0.568"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.14100","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.14100"}},"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/microsoft/GenerativeImage2Text","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":21},"by_repo_kind":{"official":{"samples":21,"ran":0,"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":"5d94233d7342dec0","entry":"collate_fn","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/data_layer/builder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/data_layer/builder.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":"5d94233d7342dec0"}},{"code_sha256_prefix":"58abe6b119b5a2b9","entry":"convert2valid","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/layers/decoder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/layers/decoder.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":"58abe6b119b5a2b9"}},{"code_sha256_prefix":"57a3be0014115531","entry":"create_decoder","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/layers/decoder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/layers/decoder.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":"57a3be0014115531"}},{"code_sha256_prefix":"b9dddc85faf8d975","entry":"create_projecton_layer","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/layers/decoder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/layers/decoder.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":"b9dddc85faf8d975"}},{"code_sha256_prefix":"f22bedfd403d31e3","entry":"dict_get_path_value","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/common.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/common.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":"f22bedfd403d31e3"}},{"code_sha256_prefix":"6f65eda04781768f","entry":"dict_has_path","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/common.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/common.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":"6f65eda04781768f"}},{"code_sha256_prefix":"da18a7817154dd3d","entry":"dict_parse_key","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/common.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/common.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":"da18a7817154dd3d"}},{"code_sha256_prefix":"6bcc61acfa076eea","entry":"evaluate_on_coco_caption","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/inference.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/inference.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":"6bcc61acfa076eea"}},{"code_sha256_prefix":"a6a3f6c029b05906","entry":"get_git_model","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/model.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/model.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":"a6a3f6c029b05906"}},{"code_sha256_prefix":"e1d4e57a259b8791","entry":"get_image_encoder","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/model.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/model.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":"e1d4e57a259b8791"}},{"code_sha256_prefix":"2012616da59774c7","entry":"get_image_transform","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/inference.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/inference.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":"2012616da59774c7"}},{"code_sha256_prefix":"4fa83e987f597120","entry":"get_inception_train_transform","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/data_layer/transform.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/data_layer/transform.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":"4fa83e987f597120"}},{"code_sha256_prefix":"e3320f89bc0f72e9","entry":"get_nick_name","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/taxonomy.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/taxonomy.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":"e3320f89bc0f72e9"}},{"code_sha256_prefix":"8c354e83280aa3fc","entry":"get_output_vocab_tokens","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/trie_decoder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/trie_decoder.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":"8c354e83280aa3fc"}},{"code_sha256_prefix":"b5c278f17b7830d7","entry":"get_trie","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/trie_decoder.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/trie_decoder.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":"b5c278f17b7830d7"}},{"code_sha256_prefix":"997799ac1eb508ab","entry":"load_image_by_pil","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/process_image.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/process_image.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":"997799ac1eb508ab"}},{"code_sha256_prefix":"a6ff5ef9a5881a56","entry":"noffset_to_synset","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/taxonomy.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/taxonomy.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":"a6ff5ef9a5881a56"}},{"code_sha256_prefix":"1054c0086f84edf2","entry":"parallel_map","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/tsv_io.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/tsv_io.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":"1054c0086f84edf2"}},{"code_sha256_prefix":"113f9525ed06575b","entry":"read_to_character","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/tsv_io.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/tsv_io.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":"113f9525ed06575b"}},{"code_sha256_prefix":"ed21fe61a5fa43b4","entry":"recursive_to_device","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/torch_common.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/torch_common.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":"ed21fe61a5fa43b4"}},{"code_sha256_prefix":"9564dcc532255c43","entry":"resize_2d_pos_embed","repo":"microsoft/GenerativeImage2Text","repo_kind":"official","path":"generativeimage2text/torch_common.py","file_url":"https://github.com/microsoft/GenerativeImage2Text/blob/HEAD/generativeimage2text/torch_common.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":"9564dcc532255c43"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}