{"id":20030639,"url":"https://github.com/peterding/albert","last_synced_at":"2026-05-24T16:38:24.956Z","repository":{"id":80368208,"uuid":"218707701","full_name":"PeterDing/albert","owner":"PeterDing","description":"An Implementation for ALBERT with Tensorflow 2.0","archived":false,"fork":false,"pushed_at":"2019-10-31T07:24:05.000Z","size":20,"stargazers_count":0,"open_issues_count":0,"forks_count":1,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-01-12T17:47:10.838Z","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":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/PeterDing.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":"2019-10-31T07:23:24.000Z","updated_at":"2019-10-31T07:24:07.000Z","dependencies_parsed_at":"2023-06-06T10:00:33.579Z","dependency_job_id":null,"html_url":"https://github.com/PeterDing/albert","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/PeterDing%2Falbert","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PeterDing%2Falbert/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PeterDing%2Falbert/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/PeterDing%2Falbert/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/PeterDing","download_url":"https://codeload.github.com/PeterDing/albert/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":241460208,"owners_count":19966519,"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":"2024-11-13T09:27:28.590Z","updated_at":"2026-05-24T16:38:19.918Z","avatar_url":"https://github.com/PeterDing.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# An Implementation for ALBERT with Tensorflow 2.0\n\nAn Implementation of [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942) with Tensorflow 2.0.\n\n## Create Training Dataset\n\n```\npython3 create_pretraining_data.py \\\n    --file_patterns=\"data/*txt\" \\\n    --max_seq_length=512 \\\n    --max_mask_length=20 \\\n    --tfrecord_file_num=8 \\\n    --whole_word_mask=False \\\n    --vocab_file='data/vocab.txt'\n```\n\n## Pre Training\n\n```\npython3 run_pretraining.py \\\n    --strategy=mirror \\\n    --model_type=base \\\n    --train_files='data-training/*' \\\n    --eval_files='data-training/*'\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpeterding%2Falbert","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpeterding%2Falbert","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpeterding%2Falbert/lists"}