{"full_name":"salesforce/BLIP","owner":"salesforce","name":"BLIP","shard":"1","url":"https://github.com/salesforce/BLIP","description":"PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation  ","homepage":"","topics":["vision-language","vision-and-language-pre-training","image-text-retrieval","image-captioning","visual-question-answering","visual-reasoning","vision-language-transformer"],"tag_pages":[],"language":"Jupyter Notebook","license":"BSD-3-Clause","avatar":"https://avatars.githubusercontent.com/u/453694?v=4","created_at":"2022-01-25T01:19:25Z","pushed_at":"2026-03-03T12:43:12Z","metrics":{"stars":5700,"forks":764,"watchers":31,"issues":211,"prs":24,"releases":0,"issues_open":128,"issues_closed":83,"prs_open":7,"prs_closed":15,"prs_merged":2,"discussions":0},"growth":{"day":{"stars":0,"forks":1,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[5702,5702,5702,5702,5701,5700,5700],"forks":[764,764,765,764,764,763,764],"watchers":[null,31,31,31,31,31,31],"issues_open":[null,128,128,128,128,128,128],"prs_open":[null,7,7,7,7,7,7]},"boards":{},"same_owner":[{"full_name":"salesforce/design-system-react","name":"design-system-react","shard":"1","boards":{}}],"issues":[{"number":165,"title":"The size of tensor a (3) must match the size of tensor b (9) at non-singleton dimension 0","comments":21,"created_at":"2023-07-07T14:22:06Z"},{"number":37,"title":"Fine tune BLIP Image Captioning to custom dataset","comments":21,"created_at":"2022-03-22T17:35:43Z"},{"number":4,"title":"minimizing difference across image and text features","comments":13,"created_at":"2022-02-02T13:13:48Z"},{"number":77,"title":"Continuously increasing RAM with Pre-training","comments":12,"created_at":"2022-07-05T13:34:02Z"},{"number":43,"title":"Training with one GPU","comments":12,"created_at":"2022-03-31T05:16:50Z"},{"number":155,"title":"BLIP Image Captioning GradCAM?","comments":8,"created_at":"2023-05-22T05:26:11Z"},{"number":18,"title":"Inference code for video-text retrieval on MSRVTT!","comments":8,"created_at":"2022-02-17T06:46:52Z"},{"number":175,"title":"Can BLIP generate more words image caption?","comments":7,"created_at":"2023-08-09T16:29:52Z"}],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}