{"id":27984479,"url":"https://github.com/git-disl/llm-topla","last_synced_at":"2026-01-26T05:07:40.243Z","repository":{"id":270702433,"uuid":"867408716","full_name":"git-disl/llm-topla","owner":"git-disl","description":null,"archived":false,"fork":false,"pushed_at":"2025-01-02T13:37:57.000Z","size":627,"stargazers_count":6,"open_issues_count":1,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-05-08T05:02:41.698Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Jupyter Notebook","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/git-disl.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}},"created_at":"2024-10-04T02:30:01.000Z","updated_at":"2025-04-08T07:36:32.000Z","dependencies_parsed_at":"2025-01-02T17:15:11.522Z","dependency_job_id":null,"html_url":"https://github.com/git-disl/llm-topla","commit_stats":null,"previous_names":["git-disl/llm-topla"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/git-disl/llm-topla","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/git-disl%2Fllm-topla","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/git-disl%2Fllm-topla/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/git-disl%2Fllm-topla/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/git-disl%2Fllm-topla/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/git-disl","download_url":"https://codeload.github.com/git-disl/llm-topla/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/git-disl%2Fllm-topla/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":28767032,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-01-26T03:54:34.369Z","status":"ssl_error","status_checked_at":"2026-01-26T03:54:33.031Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":"2025-05-08T05:01:58.945Z","updated_at":"2026-01-26T05:07:40.224Z","avatar_url":"https://github.com/git-disl.png","language":"Jupyter Notebook","funding_links":[],"categories":["2.3 Ensemble After Inference"],"sub_categories":["2.3.1 (c,1) Non Cascade"],"readme":"# LLM-TOPLA: Efficient LLM Ensemble by Maximising Diversity\n\n![alt text](./main.jpg)\n\n## Install\n\n```\n$ pip install requirements.txt\n```\n\n## Datasets\n\nMMLU and GSM8k datasets can be downloaded from the link below and must be put in `data/` folder. \n\n```\nhttps://drive.google.com/drive/folders/1DvZPrUSNoJoM-lFlF7dFWV_v6xwAyEWU?usp=sharing\n```\n\nSearchQA and XSUM datasets can be downloaded from Huggingface with the following code. The code will be called during execution.\n\n```\ndataset = load_dataset(\"EdinburghNLP/xsum\", split=dataset_name, trust_remote_code=True)\n```\n\n```\ndataset = load_dataset(\"search_qa\", \"train_test_val\", split=dataset_name, trust_remote_code=True)\n```\n\n## Basemodel Outputs\n\nThe base model outputs of these datasets are can be downloaded from the link below and must be put inside `results/`\n\n```\nhttps://drive.google.com/drive/folders/17_5JN5koFKsnyty9klNz1nBGYLKSE4tw?usp=sharing\n```\n\n\n## Run\n\nTo train LLM-TOPLA-Weighted on GSM8k or MMLU outputs of phi-2, Mixtral, and LLama\n\n```\n$ python topla_weighted.py --task_name gsm8k --model_ids 237 \n```\n\nTo train LLM-TOPLA-Summary on GSM8k or SearchQA\n\n```\n$ python topla_open_ended.py --task_name search_qa --model_ids 237 \n```\n\nTo train LLM-TOPLA-Summary on XSUM\n\n```\n$ python topla_summary.py --task_name xsum --model_ids 0123 \n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgit-disl%2Fllm-topla","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgit-disl%2Fllm-topla","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgit-disl%2Fllm-topla/lists"}