{"id":22677249,"url":"https://github.com/daemon/musent","last_synced_at":"2025-03-29T12:44:42.246Z","repository":{"id":75719955,"uuid":"119138788","full_name":"daemon/musent","owner":"daemon","description":"Extremely lightweight sentiment classifier","archived":false,"fork":false,"pushed_at":"2018-01-30T21:45:47.000Z","size":11,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-02-04T13:43:47.564Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/daemon.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":"2018-01-27T06:16:54.000Z","updated_at":"2018-01-30T21:46:18.000Z","dependencies_parsed_at":"2023-06-07T11:30:53.636Z","dependency_job_id":null,"html_url":"https://github.com/daemon/musent","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/daemon%2Fmusent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daemon%2Fmusent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daemon%2Fmusent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/daemon%2Fmusent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/daemon","download_url":"https://codeload.github.com/daemon/musent/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246187218,"owners_count":20737459,"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":[],"created_at":"2024-12-09T17:59:42.432Z","updated_at":"2025-03-29T12:44:42.224Z","avatar_url":"https://github.com/daemon.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# musent\nUsed for several NLP tasks, musent is a collection of small-footprint models. For example, at inference time for the SST binary sentiment classification task, the micro-model performs no more than a few thousand multiplies per word vector to achieve comparable accuracy, with respect to previous state-of-the-art. Even more drastically, the nano-model uses only a few dozen multiplies per **sentence** to achieve interesting results.\n\n## Installation\n\n1. Run `./getData.sh`\n2. Run `python microsem` to train a model (SST binary by default)\n\n## Results\n| Model          | SST-fine      | SST-bin    | # mult/word  |\n| -------------- |---------------|------------|--------------|\n| CNN-static     | 45.5          | 86.8       | ~90k         |\n| CNN-multi      | 47.4          | 88.1       | ~180k        |\n| CNN-nonstatic  | 48.0          | 87.2       | ~90k         |\n| musent-micro   | 47.7          | 85.9       | ~1.6k        |\n| musent-nano    | 40.6          | 83.4       | \u003c 100        |\n\nWIP\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaemon%2Fmusent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdaemon%2Fmusent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdaemon%2Fmusent/lists"}