{"id":25243220,"url":"https://github.com/macabdul9/adaptil","last_synced_at":"2025-04-05T20:42:29.039Z","repository":{"id":102552982,"uuid":"343336796","full_name":"macabdul9/Adaptil","owner":"macabdul9","description":"Investigating the Domain Robustness of Distilled Models","archived":false,"fork":false,"pushed_at":"2021-07-02T17:30:11.000Z","size":14104,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-02-12T00:45:55.858Z","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/macabdul9.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}},"created_at":"2021-03-01T08:08:26.000Z","updated_at":"2021-09-16T23:08:25.000Z","dependencies_parsed_at":"2023-04-14T11:44:18.779Z","dependency_job_id":null,"html_url":"https://github.com/macabdul9/Adaptil","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/macabdul9%2FAdaptil","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/macabdul9%2FAdaptil/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/macabdul9%2FAdaptil/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/macabdul9%2FAdaptil/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/macabdul9","download_url":"https://codeload.github.com/macabdul9/Adaptil/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247399898,"owners_count":20932876,"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":"2025-02-12T00:46:18.849Z","updated_at":"2025-04-05T20:42:29.016Z","avatar_url":"https://github.com/macabdul9.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptil\nInvestigating the Domain Robustness of Distilled Models and Pre-training models. \nMost of the experiment in this repo was presented in [Pretrained Transformers Improve Out-of-Distribution Robustness](https://arxiv.org/abs/2004.06100). Did not train models for few tasks due to minimal shift in distribution.\n\n## Tasks and Domains:\n- Sentiment Analysis (IMDB, SST2)\n- Natural Language Inference (MNLI Matching Domains/MNLI-HANS)\n- Paraphase Indentification(QQP, PAWS)\n\n\n## Representations:\n\n### Amazon Product Reviews\n![alt text](/assets/sa-amazon-review-rep-analysis.png \"Amazon Representation\")\n\n### Amazon Product Reviews\n![alt text](/assets/mnli-rep-analysis.png \"Paraphrase IID vs OOD\")\n\n### Paraphrase Indentification (QQP-PAWS)\n![alt text](/assets/paraphrase-qqp-paws.png \"Paraphrase Representation\")\n\n### WILDS Toxic Comments\n![alt text](/assets/toxic-comments-rep-analysis.png \"WILDS Representation\")\n\n\n### Sentiment Analysis (IMDB-SST2)\n![alt text](/assets/sa-imdb_sst2.png \"Sentiment Analysis Representation\")\n\n## Results (IID-vs-IID and Performance Drop(PD)):\n\n### Paraphrase (QQP-PAWS)\n\n ![alt text](/assets/paraphrase/iid-vs-ood.png \"Paraphrase IID vs OOD\")\n ![alt text](/assets/paraphrase/pd.png \"Paraphrase IID vs OOD\")\n\n### MNLI (Matched Domain)\n![alt text](/assets/mnli/iid-vs-ood.png \"Paraphrase IID vs OOD\")\n![alt text](/assets/mnli/pd.png \"MNLI IID vs OOD\")\n\n\n### Sentiment Analysis (IMDB-SST2)\n\n ![alt text](/assets/imdb_sst2-sa/iid-vs-ood.png \"Paraphrase IID vs OOD\")\n ![alt text](/assets/imdb_sst2-sa/pd.png \"Sentiment Analysis IID vs OOD\")\n\n\n\n\n\n\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmacabdul9%2Fadaptil","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmacabdul9%2Fadaptil","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmacabdul9%2Fadaptil/lists"}