{"id":13444499,"url":"https://github.com/kyegomez/MambaByte","last_synced_at":"2025-03-20T18:33:01.392Z","repository":{"id":219198312,"uuid":"748445051","full_name":"kyegomez/MambaByte","owner":"kyegomez","description":"Implementation of MambaByte in \"MambaByte: Token-free Selective State Space Model\" in Pytorch and Zeta","archived":false,"fork":false,"pushed_at":"2024-08-23T12:52:19.000Z","size":2270,"stargazers_count":100,"open_issues_count":0,"forks_count":4,"subscribers_count":6,"default_branch":"main","last_synced_at":"2024-08-31T05:22:16.233Z","etag":null,"topics":["ai","artificial-intelligence","gpt4v","machine-learning","mamba","megabyte","ml","multi-modality","tokenizer"],"latest_commit_sha":null,"homepage":"https://discord.gg/Czg5rpMZaC","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},"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":"2024-01-26T01:23:25.000Z","updated_at":"2024-08-28T11:46:16.000Z","dependencies_parsed_at":"2024-01-26T01:50:00.095Z","dependency_job_id":"d777fe41-c933-4cbf-bbec-6d0499c7051c","html_url":"https://github.com/kyegomez/MambaByte","commit_stats":null,"previous_names":["kyegomez/mambabyte"],"tags_count":0,"template":false,"template_full_name":"kyegomez/Python-Package-Template","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FMambaByte","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FMambaByte/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FMambaByte/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kyegomez%2FMambaByte/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kyegomez","download_url":"https://codeload.github.com/kyegomez/MambaByte/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":221792892,"owners_count":16881289,"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":["ai","artificial-intelligence","gpt4v","machine-learning","mamba","megabyte","ml","multi-modality","tokenizer"],"created_at":"2024-07-31T04:00:26.623Z","updated_at":"2024-10-28T06:31:08.054Z","avatar_url":"https://github.com/kyegomez.png","language":"Python","readme":"[![Multi-Modality](agorabanner.png)](https://discord.gg/qUtxnK2NMf)\n\n\n# MambaByte\nImplementation of MambaByte in \"MambaByte: Token-free Selective State Space Model\" in Pytorch and Zeta. Note this will be a higher performance implementation of Mamba with parallel scan \n\n\n## Installation\n\n```bash\npip install mambabyte\n```\n\n# Usage\n```python\nimport torch \nfrom mambabyte import MambaConfig, Mamba\n\nx = torch.randn(2, 3, 4)\n\nconfig = MambaConfig(\n    dim = 4,\n    depth = 3,\n    dt_rank = 2,\n    d_state = 2,\n    expand_factor = 2,\n    d_conv = 3,\n    dt_min = 0.001,\n    dt_max = 0.1,\n    dt_init = \"random\",\n    dt_scale = 1.0,\n    bias = False,\n    conv_bias = True,\n    pscan = True\n)\n\nmodel = Mamba(config)\n\nout = model(x)\n\nprint(out)\n\n```\n\n\n# License\nMIT\n","funding_links":["https://github.com/sponsors/kyegomez"],"categories":["On the replacement of transformer/attention by SSMs","Python","NLP"],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyegomez%2FMambaByte","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkyegomez%2FMambaByte","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkyegomez%2FMambaByte/lists"}