{"id":31211496,"url":"https://github.com/cyberagentailab/condlora","last_synced_at":"2025-09-21T05:27:35.178Z","repository":{"id":231437521,"uuid":"781763140","full_name":"CyberAgentAILab/CondLoRA","owner":"CyberAgentAILab","description":"Code for our paper \"A Single Linear Layer Yields Task-Adapted Low-Rank Matrices\"","archived":false,"fork":false,"pushed_at":"2024-04-04T01:56:58.000Z","size":156,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-09-10T07:42:52.037Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/2403.14946","language":"Python","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/CyberAgentAILab.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-04-04T01:41:38.000Z","updated_at":"2025-09-02T07:14:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"220d0ce7-1104-443d-b243-9866f7659d1b","html_url":"https://github.com/CyberAgentAILab/CondLoRA","commit_stats":null,"previous_names":["cyberagentailab/condlora"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CyberAgentAILab/CondLoRA","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FCondLoRA","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FCondLoRA/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FCondLoRA/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FCondLoRA/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab","download_url":"https://codeload.github.com/CyberAgentAILab/CondLoRA/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2FCondLoRA/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276195623,"owners_count":25601151,"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","status":"online","status_checked_at":"2025-09-21T02:00:07.055Z","response_time":72,"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":[],"created_at":"2025-09-21T05:27:33.276Z","updated_at":"2025-09-21T05:27:35.170Z","avatar_url":"https://github.com/CyberAgentAILab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CondLoRA\n\n## How to use\n\n### Environment\n- OS: Debian GNU/Linux 10 (buster)\n- Python version: 3.8.5\n- CUDA version: 11.3.109\n\n### Install libraries\n\n```\npip install -r requirements.txt\ncd ConditionalLoRA\npython setup.py install\n```\n\n### Hyperparameter (learning rate) search \n\n```\ncd experiments\nbash hp_search.sh [GPU number] [GLEU task name (e.g. sst2, mnli, etc.)] [lora type (e.g. lora, adalora, conditional_lora)] [seed number]\n```\n\n### Train Model\n\n```\ncd experiments/[GLEU task name (e.g. sst2, mnli, etc.)]\nbash train.sh [GPU number] [lora type (e.g. lora, adalora, conditional_lora)] [seed number]\n```\n\n### Evaluate Model\n\n```\npython src/evaluate.py --model_path [path to trained lora model] --task [GLEU task name (e.g. sst2, mnli, etc.)] --batch_size [batch size] --max_length [max length of input text]\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fcondlora","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyberagentailab%2Fcondlora","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fcondlora/lists"}