{"id":51220958,"url":"https://github.com/huggon1/ml-algorithm-implementations","last_synced_at":"2026-06-28T07:03:06.209Z","repository":{"id":344488553,"uuid":"1181691544","full_name":"huggon1/ml-algorithm-implementations","owner":"huggon1","description":"Educational implementations for ML, DL, LLM blocks, ViT, and CUDA.","archived":false,"fork":false,"pushed_at":"2026-03-14T14:00:39.000Z","size":690,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-03-15T09:13:26.071Z","etag":null,"topics":["cuda","machine-learning","numpy","pytorch","vision-transformer"],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/huggon1.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-03-14T13:49:50.000Z","updated_at":"2026-03-14T14:01:10.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/huggon1/ml-algorithm-implementations","commit_stats":null,"previous_names":["huggon1/ml-algorithm-implementations"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/huggon1/ml-algorithm-implementations","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggon1%2Fml-algorithm-implementations","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggon1%2Fml-algorithm-implementations/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggon1%2Fml-algorithm-implementations/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggon1%2Fml-algorithm-implementations/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/huggon1","download_url":"https://codeload.github.com/huggon1/ml-algorithm-implementations/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/huggon1%2Fml-algorithm-implementations/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34880191,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-28T02:00:05.809Z","response_time":54,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"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":["cuda","machine-learning","numpy","pytorch","vision-transformer"],"created_at":"2026-06-28T07:03:05.212Z","updated_at":"2026-06-28T07:03:06.199Z","avatar_url":"https://github.com/huggon1.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# ml-algorithm-implementations\n\nA curated collection of small algorithm and deep learning implementations collected from personal study projects.\n\n## Highlights\n\n- Classic ML implementations in NumPy notebooks\n- Foundational neural network modules and sequence models in PyTorch\n- Focused LLM building blocks such as RoPE and LoRA\n- ViT and CUDA study code collected into one repository\n\n## Scope\n\nThis repository focuses on readable educational code rather than polished production packages.\n\nIncluded areas:\n\n- Numpy implementations\n- PyTorch fundamentals\n- PyTorch sequence models and transformer examples\n- Small LLM building blocks such as RoPE and LoRA\n- MindSpore ViT experiments\n- CUDA lessons and kernel demos\n\n## Structure\n\n```text\nml-algorithm-implementations/\n  numpy/\n    decision_tree/\n    kmeans/\n  pytorch/\n    llm_blocks/\n  mindspore/\n    vit/\n  cuda/\n```\n\n## Notes\n\n- Some files are self-contained runnable demos.\n- Some files are study-oriented reference implementations and may need small environment-specific adjustments before training.\n- Large checkpoints, IDE files, caches, and unrelated materials are intentionally omitted.\n\n## Suggested Environment\n\nThis repository mixes several stacks, so the exact dependencies depend on which folder you want to run:\n\n- `numpy/`: Jupyter, NumPy, Matplotlib\n- `pytorch/`: PyTorch\n- `mindspore/`: MindSpore\n- `cuda/`: CUDA toolkit and a compatible compiler toolchain\n\nFor the lightweight Python subset:\n\n```bash\npip install -r requirements.txt\n```\n\nFor CUDA lessons, use the local README files in `cuda/` as the primary entry points because they explain the lesson order and supporting images.\n\n## Highlights\n\n- `numpy/decision_tree` and `numpy/kmeans` keep notebook-style implementations.\n- `pytorch/` collects neural network basics such as MLP, CNN, RNN, LSTM, Seq2Seq, and Transformer.\n- `pytorch/llm_blocks` keeps a few focused LLM-related experiments.\n- `mindspore/vit` preserves the ViT implementation in MindSpore.\n- `cuda/` keeps the lesson-based CUDA exploration code and notes.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuggon1%2Fml-algorithm-implementations","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fhuggon1%2Fml-algorithm-implementations","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fhuggon1%2Fml-algorithm-implementations/lists"}