{"id":23690184,"url":"https://github.com/kolhesamiksha/nemo_curator","last_synced_at":"2026-01-15T01:30:18.186Z","repository":{"id":269643310,"uuid":"904373017","full_name":"kolhesamiksha/Nemo_Curator","owner":"kolhesamiksha","description":"This repository contains a sample text data-preparation code using Nemo Curator for pre-training or synthetic data generation","archived":false,"fork":false,"pushed_at":"2024-12-25T04:39:23.000Z","size":130,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-12-25T05:28:29.215Z","etag":null,"topics":["curator","data-preprocessing-pipelines","finetuning-llms","generative-ai","nemo","nvidia","synthetic-dataset-generation"],"latest_commit_sha":null,"homepage":"","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/kolhesamiksha.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":"2024-12-16T19:02:55.000Z","updated_at":"2024-12-25T04:39:26.000Z","dependencies_parsed_at":"2024-12-25T05:28:31.696Z","dependency_job_id":"16502eba-b6fa-433f-9393-f78e12e1cb5e","html_url":"https://github.com/kolhesamiksha/Nemo_Curator","commit_stats":null,"previous_names":["kolhesamiksha/nemo_curator"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kolhesamiksha%2FNemo_Curator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kolhesamiksha%2FNemo_Curator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kolhesamiksha%2FNemo_Curator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/kolhesamiksha%2FNemo_Curator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/kolhesamiksha","download_url":"https://codeload.github.com/kolhesamiksha/Nemo_Curator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239753736,"owners_count":19691162,"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":["curator","data-preprocessing-pipelines","finetuning-llms","generative-ai","nemo","nvidia","synthetic-dataset-generation"],"created_at":"2024-12-30T01:59:53.866Z","updated_at":"2026-01-15T01:30:18.114Z","avatar_url":"https://github.com/kolhesamiksha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Nemo_Curator\nThis repository contains a sample text data-preparation code using Nemo Curator for pre-training or synthetic data generation\n\n![image](https://github.com/user-attachments/assets/b28fe3ee-fe06-4c51-a2ef-d6cc702cc4ae)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkolhesamiksha%2Fnemo_curator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkolhesamiksha%2Fnemo_curator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkolhesamiksha%2Fnemo_curator/lists"}