{"id":14995765,"url":"https://github.com/tjkessler/mojoml","last_synced_at":"2026-03-19T19:44:25.483Z","repository":{"id":214900308,"uuid":"737619794","full_name":"tjkessler/mojoml","owner":"tjkessler","description":"Linear algebra and machine learning in Mojo 🔥","archived":false,"fork":false,"pushed_at":"2024-01-07T03:28:42.000Z","size":1707,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-22T06:48:21.440Z","etag":null,"topics":["linear-algebra","machine-learning","modular","mojo"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/tjkessler.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"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}},"created_at":"2023-12-31T19:22:53.000Z","updated_at":"2024-04-27T03:08:36.000Z","dependencies_parsed_at":"2024-01-07T04:24:58.021Z","dependency_job_id":null,"html_url":"https://github.com/tjkessler/mojoml","commit_stats":null,"previous_names":["tjkessler/mojoml"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjkessler%2Fmojoml","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjkessler%2Fmojoml/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjkessler%2Fmojoml/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/tjkessler%2Fmojoml/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/tjkessler","download_url":"https://codeload.github.com/tjkessler/mojoml/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243762267,"owners_count":20343979,"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":["linear-algebra","machine-learning","modular","mojo"],"created_at":"2024-09-24T16:19:48.073Z","updated_at":"2026-01-03T01:08:00.739Z","avatar_url":"https://github.com/tjkessler.png","language":null,"funding_links":[],"categories":["Machine Learning"],"sub_categories":[],"readme":"# mojoml 🔥\n\nLinear algebra and machine learning in Mojo 🔥\n\n(Heavily inspired by the [official Mojo documentation](https://docs.modular.com/mojo/))\n\n## Usage\n\nMove the `mojoml.mojopkg` file to your current working directory, or build from source with:\n\n```\n$ git clone https://github.com/tjkessler/mojoml\n$ cd mojoml\n$ mojo package mojoml -o mojoml.mojopkg\n```\n\nMatrix operations:\n\n```python\nfrom mojoml.structs import Matrix\nfrom mojoml.structs.generators import random_matrix\nfrom mojoml.linalg import matmul, norm, transpose\n\n\nfn main() -\u003e None:\n\n    let m1: Matrix = random_matrix(16, 32)\n    let m2: Matrix = random_matrix(32, 48)\n\n    # m_matmul \u003c- m1 @ m2\n    let m_matmul: Matrix = Matrix(16, 48)\n    matmul(m_matmul, m1, m2)\n\n    let m3: Matrix = random_matrix(32, 32)\n    let m3_norm: Float32 = norm(m3)\n\n    # m1_T \u003c- m1.T\n    let m1_T: Matrix = Matrix(32, 16)\n    transpose(m1_T, m1)\n```\n\nFeed-forward, activation, loss (more to come!):\n\n```python\nfrom mojoml.structs import Matrix\nfrom mojoml.structs.generators import random_matrix\nfrom mojoml.nn import Linear\nfrom mojoml.nn.functional import mse_loss, relu, sigmoid\n\n\nfn main() -\u003e None:\n\n    # define a layer with 16 inputs, 32 outputs\n    let layer: Linear = Linear(16, 32)\n\n    # data to feed forward; 8 samples, 16 features per sample\n    let inputs: Matrix = random_matrix(8, 16)\n\n    # output shape is 8 samples, 32 outputs per sample\n    let outputs: Matrix = Matrix(8, 32)\n\n    # Y \u003c- X @ W.T + B\n    layer.forward(outputs, inputs)\n\n    # apply ReLU activation\n    let out_relu: Matrix = Matrix(8, 32)\n    relu(out_relu, outputs)\n\n    # apply sigmoid activation\n    let out_sigmoid: Matrix = Matrix(8, 32)\n    sigmoid(out_sigmoid, outputs)\n\n    # calculate MSE loss w/ dummy target values\n    let targets: Matrix = random_matrix(8, 32)\n    let loss_mat: Matrix = Matrix(1, 1)\n    mse_loss(loss_mat, out_sigmoid, targets)\n    let mse: Float32 = loss_mat[0, 0]\n\n    # TODO: gradient descent!\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftjkessler%2Fmojoml","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftjkessler%2Fmojoml","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftjkessler%2Fmojoml/lists"}