{"id":20602428,"url":"https://github.com/augustunderground/prehsept","last_synced_at":"2026-05-02T11:40:24.268Z","repository":{"id":47055982,"uuid":"393958051","full_name":"AugustUnderground/prehsept","owner":"AugustUnderground","description":"Modeling the behaviour of primitive devices with Hasktorch.","archived":false,"fork":false,"pushed_at":"2023-08-23T09:09:50.000Z","size":440,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-01-17T02:08:13.040Z","etag":null,"topics":["gm-over-id","haskell","hasktorch","machine-learning","transistor-characterization"],"latest_commit_sha":null,"homepage":"https://augustunderground.github.io/prehsept/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/AugustUnderground.png","metadata":{"files":{"readme":"README.md","changelog":"ChangeLog.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-08-08T12:45:29.000Z","updated_at":"2022-07-22T12:29:10.000Z","dependencies_parsed_at":"2023-01-22T09:31:03.032Z","dependency_job_id":null,"html_url":"https://github.com/AugustUnderground/prehsept","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AugustUnderground%2Fprehsept","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AugustUnderground%2Fprehsept/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AugustUnderground%2Fprehsept/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/AugustUnderground%2Fprehsept/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/AugustUnderground","download_url":"https://codeload.github.com/AugustUnderground/prehsept/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":242244815,"owners_count":20095982,"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":["gm-over-id","haskell","hasktorch","machine-learning","transistor-characterization"],"created_at":"2024-11-16T09:13:51.040Z","updated_at":"2026-05-02T11:40:19.233Z","avatar_url":"https://github.com/AugustUnderground.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# prehsept\n\nModeling the behaviour of primitive devices around the operating point in\nhaskell.\n\n## Setup\n\nRequires [libtorch](https://pytorch.org/get-started/locally/) symlinked into\nthe root of this repository according to `extra-include-dirs` and\n`extra-lib-dirs` in `stack.yaml`.\n\nThe `setenv` script can be sourced to export the correct `LD_LIBRARY_PATH`.\nAdditionally it exports the `DEVICE` variable, supposedly enabling GPU support\nin Hasktorch (I'm not sure how/if it works).\n\n```sh\n$ source setenv\n```\n\n## Usage\n\nBuild the project with stack\n\n```sh\n$ stack build\n```\n\nthen run it\n\n```sh\n$ stack run\n```\n\n### CLI\n\nThe executable part supports the following arguments:\n\n```bash\nPrimitive Device Modeling Around the Operating Point\n\nUsage: prehsept-exe [-k|--pdk PDK] [-d|--dev DEV] (-p|--dir DIR) [-n|--num NUM]\n                    [-r|--reg REGION] [-s|--size SIZE]\n  PREHSEPT\n\nAvailable options:\n  -k,--pdk PDK             PDK from which the data was generated\n                           (default: xh035)\n  -d,--dev DEV             Device Type: nmos | pmos (default: nmos)\n  -p,--dir DIR             Path to lookup-table as tensor\n  -n,--num NUM             Number of Epochs (default: 25)\n  -r,--reg REGION          Region of Operation: 2 | 3 (default: 2)\n  -e,--exp                 Experimental Mapping\n  -s,--size SIZE           Batch Size (default: 5000)\n  -h,--help                Show this help text\n```\n\nFor example, to train a GPDK180 NMOS model for 100 epochs with a batch size of\n32 run:\n\n```bash\nstack exec -- prehsept-exe --pdk gpdk180 --dev nmos --dir ./data/gpdk180-pmos.pt --size 32 --num 100\n```\n\n## Notebooks\n\nThe notebooks can be viewed locally by running the jupyter server in the\n`./notebooks` directory:\n\n```bash\n$ stack exec jupyter -- notebook\n```\n\n[IHaskell](https://github.com/IHaskell/IHaskell) must be installed for this to\nwork.\n\n## License\n\nBSD3\n\n## Thanks\n\nThanks to the [hastorch](https://github.com/hasktorch/hasktorch) project!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faugustunderground%2Fprehsept","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faugustunderground%2Fprehsept","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faugustunderground%2Fprehsept/lists"}