{"full_name":"facebookresearch/mmf","owner":"facebookresearch","name":"mmf","shard":"1","url":"https://github.com/facebookresearch/mmf","description":"A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)","homepage":"https://mmf.sh/","topics":["pytorch","vqa","pretrained-models","multimodal","deep-learning","captioning","dialog","textvqa","hateful-memes","multi-tasking"],"tag_pages":["deep-learning","dialog","multimodal","pretrained-models","pytorch"],"language":"Python","license":"NOASSERTION","avatar":"https://avatars.githubusercontent.com/u/16943930?v=4","created_at":"2018-06-27T04:52:40Z","pushed_at":"2026-10-06T20:36:42Z","metrics":{"stars":5633,"forks":941,"watchers":108,"issues":659,"prs":676,"releases":2,"issues_open":115,"issues_closed":544,"prs_open":35,"prs_closed":592,"prs_merged":49,"discussions":0},"growth":{"day":{"stars":0,"forks":0,"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":[5633,5633,5633,5633,5633,5633,5633],"forks":[941,941,941,941,941,941,941],"watchers":[null,108,108,108,108,108,108],"issues_open":[null,115,115,115,115,115,115],"prs_open":[null,35,35,35,35,35,35]},"boards":{},"same_owner":[{"full_name":"facebookresearch/AugLy","name":"AugLy","shard":"1","boards":{}},{"full_name":"facebookresearch/ImageBind","name":"ImageBind","shard":"1","boards":{}},{"full_name":"facebookresearch/audiocraft","name":"audiocraft","shard":"1","boards":{}},{"full_name":"facebookresearch/codellama","name":"codellama","shard":"1","boards":{}},{"full_name":"facebookresearch/detectron2","name":"detectron2","shard":"1","boards":{}},{"full_name":"facebookresearch/detr","name":"detr","shard":"1","boards":{}},{"full_name":"facebookresearch/dinov2","name":"dinov2","shard":"1","boards":{}},{"full_name":"facebookresearch/dinov3","name":"dinov3","shard":"1","boards":{}},{"full_name":"facebookresearch/faiss","name":"faiss","shard":"1","boards":{}},{"full_name":"facebookresearch/fastText","name":"fastText","shard":"1","boards":{}},{"full_name":"facebookresearch/hydra","name":"hydra","shard":"1","boards":{}},{"full_name":"facebookresearch/maskrcnn-benchmark","name":"maskrcnn-benchmark","shard":"1","boards":{}},{"full_name":"facebookresearch/pifuhd","name":"pifuhd","shard":"1","boards":{}},{"full_name":"facebookresearch/pytorch3d","name":"pytorch3d","shard":"1","boards":{}},{"full_name":"facebookresearch/sam2","name":"sam2","shard":"1","boards":{}},{"full_name":"facebookresearch/sam3","name":"sam3","shard":"1","boards":{}},{"full_name":"facebookresearch/seamless_communication","name":"seamless_communication","shard":"1","boards":{}},{"full_name":"facebookresearch/segment-anything","name":"segment-anything","shard":"1","boards":{}},{"full_name":"facebookresearch/vggt","name":"vggt","shard":"1","boards":{}}],"issues":[{"number":1037,"title":"TextVQA","comments":7,"created_at":"2021-07-31T13:12:13Z"},{"number":1010,"title":"Is there a clear cut demo for using the pre-trained M4C Captioner model available on sample images?","comments":7,"created_at":"2021-07-10T22:44:23Z"},{"number":946,"title":"errors while running pytests .\\test","comments":7,"created_at":"2021-05-16T14:05:53Z"},{"number":969,"title":"model_name of pre-trained Pythia model for VQA ","comments":6,"created_at":"2021-06-14T11:24:29Z"},{"number":1221,"title":"mmf hateful memes challenge dataset","comments":5,"created_at":"2022-03-27T20:32:52Z"},{"number":999,"title":"Update VizWiz annotations/features","comments":5,"created_at":"2021-07-01T14:49:22Z"},{"number":980,"title":"errors while running krisp code","comments":5,"created_at":"2021-06-22T07:46:40Z"},{"number":1219,"title":"FLAVA code","comments":4,"created_at":"2022-03-25T17:23:29Z"}],"discussions":[],"latest_release":{"name":"","tag":"v0.3.1","published_at":"2019-08-26T19:04:21Z","body":"","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}