{"id":19156179,"url":"https://github.com/kyegomez/kosmosg","last_synced_at":"2025-05-07T07:35:01.824Z","repository":{"id":198979804,"uuid":"701933713","full_name":"kyegomez/KosmosG","owner":"kyegomez","description":"My implementation of the model KosmosG from \"KOSMOS-G: Generating Images in Context with Multimodal Large Language Models\" ","archived":false,"fork":false,"pushed_at":"2024-11-11T03:57:59.000Z","size":2928,"stargazers_count":14,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-19T19:47:20.228Z","etag":null,"topics":["attention-is-all-you-need","attention-mechanism","attention-mechanisms","computer-vision","multimodal","multimodal-learning"],"latest_commit_sha":null,"homepage":"https://discord.gg/qUtxnK2NMf","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/kyegomez.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null},"funding":{"github":["kyegomez"],"patreon":null,"open_collective":null,"ko_fi":null,"tidelift":null,"community_bridge":null,"liberapay":null,"issuehunt":null,"otechie":null,"lfx_crowdfunding":null,"custom":null}},"created_at":"2023-10-08T02:10:42.000Z","updated_at":"2024-08-02T07:51:27.000Z","dependencies_parsed_at":null,"dependency_job_id":"bebba08d-9040-43d1-8b1c-0584eb516990","html_url":"https://github.com/kyegomez/KosmosG","commit_stats":null,"previous_names":["kyegomez/kosmosg"],"tags_count":0,"template":false,"template_full_name":"kyegomez/Python-Package-Template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FKosmosG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FKosmosG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FKosmosG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FKosmosG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kyegomez","download_url":"https://codeload.github.com/kyegomez/KosmosG/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252834182,"owners_count":21811331,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["attention-is-all-you-need","attention-mechanism","attention-mechanisms","computer-vision","multimodal","multimodal-learning"],"created_at":"2024-11-09T08:33:31.211Z","updated_at":"2025-05-07T07:35:01.802Z","avatar_url":"https://github.com/kyegomez.png","language":"Python","funding_links":["https://github.com/sponsors/kyegomez"],"categories":[],"sub_categories":[],"readme":"[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n# KosmosG\nMy implementation of the model KosmosG from \"KOSMOS-G: Generating Images in Context with Multimodal Large Language Models\"\n\n## Installation\n`pip install kosmosg`\n\n## Usage\n```python\nimport torch\nfrom kosmosg.main import KosmosG\n\n# usage\nimg = torch.randn(1, 3, 256, 256)\ntext = torch.randint(0, 20000, (1, 1024))\n\nmodel = KosmosG()\noutput = model(img, text)\nprint(output)\n```\n\n## Architecture\n`text, image =\u003e KosmosG =\u003e text tokens with multi modality understanding`\n\n## License\nMIT\n\n## Todo\n- Create Aligner in pytorch\n- Create Diffusion module\n- Integrate these pieces\n- Create a training script","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyegomez%2Fkosmosg","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkyegomez%2Fkosmosg","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyegomez%2Fkosmosg/lists"}