{"id":26896947,"url":"https://github.com/fisheeped/creek","last_synced_at":"2025-04-01T04:02:29.977Z","repository":{"id":231903128,"uuid":"782996553","full_name":"fisheeped/creek","owner":"fisheeped","description":"生成模型 tokenizer训练，模型初始化，模型预训练，指令微调。llama，creek","archived":false,"fork":false,"pushed_at":"2024-12-13T01:53:38.000Z","size":823,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-12-13T02:30:44.068Z","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/fisheeped.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":"2024-04-06T16:40:02.000Z","updated_at":"2024-12-13T01:53:42.000Z","dependencies_parsed_at":null,"dependency_job_id":"21c19885-0e80-4176-9f46-e7f21ad9454a","html_url":"https://github.com/fisheeped/creek","commit_stats":null,"previous_names":["fisheeped/creek"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fisheeped%2Fcreek","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fisheeped%2Fcreek/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fisheeped%2Fcreek/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fisheeped%2Fcreek/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fisheeped","download_url":"https://codeload.github.com/fisheeped/creek/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246580468,"owners_count":20800111,"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":"2025-04-01T04:02:24.731Z","updated_at":"2025-04-01T04:02:29.971Z","avatar_url":"https://github.com/fisheeped.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"🤗https://huggingface.co/maheer/creek\n\n# 从零创建生成大模型\n下面代码中的参数，资源占用：预训练A800*8，每张卡显存占用70G+。\n可以调小batch_size,max_length，最少单卡12G显存应该能完成下面步骤。\n\n\n**train tokenizer** \n```shell\npython model_init/tokenization/train_eval_tokenizer.py\n```\n**init model** \n```shell\npython model_init/model_init.py\n```\n**pretrain**\n```shell\nbash pretrain.sh\n```\n**finetune**\n```shell\nbash sft.sh\n```\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffisheeped%2Fcreek","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffisheeped%2Fcreek","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffisheeped%2Fcreek/lists"}