{"id":19054745,"url":"https://github.com/ssbuild/baichuan_finetuning","last_synced_at":"2025-04-24T03:29:52.007Z","repository":{"id":180307400,"uuid":"664917659","full_name":"ssbuild/baichuan_finetuning","owner":"ssbuild","description":"baichuan and baichuan2 finetuning and alpaca finetuning","archived":false,"fork":false,"pushed_at":"2025-03-10T04:57:52.000Z","size":517,"stargazers_count":32,"open_issues_count":3,"forks_count":0,"subscribers_count":2,"default_branch":"dev","last_synced_at":"2025-04-18T12:17:54.236Z","etag":null,"topics":["baichuan","baichuan-13b","baichuan-13b-chat","baichuan-chat","baichuan2-13b","baichuan2-13b-chat","fineturn","qlora"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ssbuild.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2023-07-11T03:33:49.000Z","updated_at":"2024-04-21T17:14:52.000Z","dependencies_parsed_at":"2025-04-17T23:39:12.046Z","dependency_job_id":"cbbf6ea3-d68b-4939-880f-8ec4bd0e7b64","html_url":"https://github.com/ssbuild/baichuan_finetuning","commit_stats":null,"previous_names":["ssbuild/baichuan2_finetuning","ssbuild/baichuan_finetuning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fbaichuan_finetuning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fbaichuan_finetuning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fbaichuan_finetuning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ssbuild%2Fbaichuan_finetuning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ssbuild","download_url":"https://codeload.github.com/ssbuild/baichuan_finetuning/tar.gz/refs/heads/dev","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250555707,"owners_count":21449853,"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":["baichuan","baichuan-13b","baichuan-13b-chat","baichuan-chat","baichuan2-13b","baichuan2-13b-chat","fineturn","qlora"],"created_at":"2024-11-08T23:39:40.745Z","updated_at":"2025-04-24T03:29:51.990Z","avatar_url":"https://github.com/ssbuild.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## update\r\n```text\r\n    2024-04-22 简化\r\n    2023-10-09 support accelerator trainer\r\n    2023-10-07 support colossalai trainer\r\n    2023-09-26 support transformers trainer\r\n    2023-09-15 deep_training \u003e= 0.2.2.post4\r\n    2023-09-08 fix baichuan ptv2\r\n    2023-09-06 整合baichuan finetuning ,  support baichuan2 finetuning\r\n```\r\n   \r\n\r\n## install\r\n- [deep_training](https://github.com/ssbuild/deep_training)\r\n- pip install -U -r requirements.txt\r\n- 如果无法安装， 可以切换官方源 pip install -i https://pypi.org/simple -U -r requirements.txt\r\n\r\n\r\n```text\r\ndev 通过一下方式安装 , 注意顺序\r\npip uninstall aigc_zoo\r\npip install -U git+https://github.com/ssbuild/aigc_zoo#egg=aigc_zoo\r\n```\r\n\r\n\r\n## v1 weight\r\n- [Baichuan-13B-Base](https://huggingface.co/baichuan-inc/Baichuan-13B-Base)\r\n- [Baichuan-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan-13B-Chat)\r\n- [baichuan-13b-chat-int4](https://huggingface.co/ssbuild/baichuan-13b-chat-int4)\r\n\r\n## v2 weight\r\n- [Baichuan2-7B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-7B-Chat)\r\n- [Baichuan2-7B-Base](https://huggingface.co/baichuan-inc/Baichuan2-7B-Base)\r\n- [baichuan2-7b-chat-int4](https://huggingface.co/ssbuild/baichuan2-7b-chat-int4)\r\n- \r\n- [Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat)\r\n- [Baichuan2-13B-Base](https://huggingface.co/baichuan-inc/Baichuan2-13B-Base)\r\n- [baichuan2-13b-chat-int4](https://huggingface.co/ssbuild/baichuan2-13b-chat-int4)\r\n\r\n\r\n\r\n\r\n\r\n## data sample\r\n- [open_data 不定时更新数据集](https://github.com/ssbuild/open_data)\r\n   \r\n单条数据示例\r\n```text\r\nrole one of user system function assistant\r\nq question optional\r\na answer   must\r\n```\r\n\r\n```json\r\n{\"id\": 1, \"paragraph\": [{\"q\": \"从南京到上海的路线\", \"a\": \"你好，南京到上海的路线如下：\\n1. 南京到上海，可以乘坐南京地铁1号线，在南京站乘坐轨道交通1号线。\\n2. 南京到浦东机场，可以搭乘上海地铁1号，在陆家嘴站乘坐地铁1线，在浦东国际机场站乘坐机场快线，前往上海浦东国际机场。\\n3. 上海到南京，可以换乘上海地铁2号线，从南京站换乘地铁2线，再从南京南站换乘地铁1路，然后到达上海站\"}]}\r\n{\"id\": 2, \"paragraph\": [{\"q\": \"写一个诗歌，关于冬天\", \"a\": \"冬夜寂静冷，\\n云在天边飘，\\n冰封白雪上， \\n寒冷像一场雪。\\n \\n雪花融化成冰，\\n像那雪花飘洒，\\n在寒冷的冬天，\\n感受春天的喜悦。\\n 冬日里，\\n风雪渐消，\\n一片寂静，\\n把快乐和温暖带回家。\"}]}\r\n{\"id\": 3, \"paragraph\": [{\"q\": \"晚上睡不着应该怎么办\", \"a\": \"晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法:\\n\\n1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。\\n2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。\\n3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。\\n4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。\\n5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。\\n6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。\\n\\n如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。\"}]}\r\n\r\n```\r\n\r\n或者\r\n\r\n```json\r\n{\"id\": 1, \"conversations\": [{\"from\": \"user\", \"value\": \"从南京到上海的路线\"}, {\"from\": \"assistant\", \"value\": \"你好，南京到上海的路线如下：\\n1. 南京到上海，可以乘坐南京地铁1号线，在南京站乘坐轨道交通1号线。\\n2. 南京到浦东机场，可以搭乘上海地铁1号，在陆家嘴站乘坐地铁1线，在浦东国际机场站乘坐机场快线，前往上海浦东国际机场。\\n3. 上海到南京，可以换乘上海地铁2号线，从南京站换乘地铁2线，再从南京南站换乘地铁1路，然后到达上海站\"}]}\r\n{\"id\": 2, \"conversations\": [{\"from\": \"user\", \"value\": \"写一个诗歌，关于冬天\"}, {\"from\": \"assistant\", \"value\": \"冬夜寂静冷，\\n云在天边飘，\\n冰封白雪上， \\n寒冷像一场雪。\\n \\n雪花融化成冰，\\n像那雪花飘洒，\\n在寒冷的冬天，\\n感受春天的喜悦。\\n 冬日里，\\n风雪渐消，\\n一片寂静，\\n把快乐和温暖带回家。\"}]}\r\n{\"id\": 3, \"conversations\": [{\"from\": \"user\", \"value\": \"晚上睡不着应该怎么办\"}, {\"from\": \"assistant\", \"value\": \"晚上睡不着可能会让你感到焦虑或不舒服,但以下是一些可以帮助你入睡的方法:\\n\\n1. 制定规律的睡眠时间表:保持规律的睡眠时间表可以帮助你建立健康的睡眠习惯,使你更容易入睡。尽量在每天的相同时间上床,并在同一时间起床。\\n2. 创造一个舒适的睡眠环境:确保睡眠环境舒适,安静,黑暗且温度适宜。可以使用舒适的床上用品,并保持房间通风。\\n3. 放松身心:在睡前做些放松的活动,例如泡个热水澡,听些轻柔的音乐,阅读一些有趣的书籍等,有助于缓解紧张和焦虑,使你更容易入睡。\\n4. 避免饮用含有咖啡因的饮料:咖啡因是一种刺激性物质,会影响你的睡眠质量。尽量避免在睡前饮用含有咖啡因的饮料,例如咖啡,茶和可乐。\\n5. 避免在床上做与睡眠无关的事情:在床上做些与睡眠无关的事情,例如看电影,玩游戏或工作等,可能会干扰你的睡眠。\\n6. 尝试呼吸技巧:深呼吸是一种放松技巧,可以帮助你缓解紧张和焦虑,使你更容易入睡。试着慢慢吸气,保持几秒钟,然后缓慢呼气。\\n\\n如果这些方法无法帮助你入睡,你可以考虑咨询医生或睡眠专家,寻求进一步的建议。\"}]}\r\n```\r\n\r\n\r\n\r\n## infer\r\n    # infer_finetuning.py 推理微调模型\r\n    # infer_lora_finetuning.py 推理微调模型\r\n    # infer_ptuning.py 推理p-tuning-v2微调模型\r\n     python infer_finetuning.py\r\n![infer](assets/1.png)\r\n![infer](assets/2.png)\r\n\r\n## training\r\n```text\r\n    # 制作数据\r\n    cd scripts\r\n    bash train_full.sh -m dataset \r\n    or\r\n    bash train_lora.sh -m dataset \r\n    or\r\n    bash train_ptv2.sh -m dataset \r\n    \r\n    注: num_process_worker 为多进程制作数据 ， 如果数据量较大 ， 适当调大至cpu数量\r\n    dataHelper.make_dataset_with_args(data_args.train_file,mixed_data=False, shuffle=True,mode='train',num_process_worker=0)\r\n    \r\n    # 全参数训练 \r\n        bash train_full.sh -m train\r\n        \r\n    # lora adalora ia3 \r\n        bash train_lora.sh -m train\r\n        \r\n    # ptv2\r\n        bash train_ptv2.sh -m train\r\n```\r\n   \r\n## 训练参数\r\n[训练参数](args.MD)\r\n\r\n## 友情链接\r\n\r\n- [pytorch-task-example](https://github.com/ssbuild/pytorch-task-example)\r\n- [moss_finetuning](https://github.com/ssbuild/moss_finetuning)\r\n- [chatglm_finetuning](https://github.com/ssbuild/chatglm_finetuning)\r\n- [chatglm2_finetuning](https://github.com/ssbuild/chatglm2_finetuning)\r\n- [chatglm3_finetuning](https://github.com/ssbuild/chatglm3_finetuning)\r\n- [t5_finetuning](https://github.com/ssbuild/t5_finetuning)\r\n- [llm_finetuning](https://github.com/ssbuild/llm_finetuning)\r\n- [llm_rlhf](https://github.com/ssbuild/llm_rlhf)\r\n- [chatglm_rlhf](https://github.com/ssbuild/chatglm_rlhf)\r\n- [t5_rlhf](https://github.com/ssbuild/t5_rlhf)\r\n- [rwkv_finetuning](https://github.com/ssbuild/rwkv_finetuning)\r\n- [baichuan_finetuning](https://github.com/ssbuild/baichuan_finetuning)\r\n- [xverse_finetuning](https://github.com/ssbuild/xverse_finetuning)\r\n- [internlm_finetuning](https://github.com/ssbuild/internlm_finetuning)\r\n- [qwen_finetuning](https://github.com/ssbuild/qwen_finetuning)\r\n- [skywork_finetuning](https://github.com/ssbuild/skywork_finetuning)\r\n- [bluelm_finetuning](https://github.com/ssbuild/bluelm_finetuning)\r\n- [yi_finetuning](https://github.com/ssbuild/yi_finetuning)\r\n\r\n## \r\n    纯粹而干净的代码\r\n\r\n## Star History\r\n\r\n[![Star History Chart](https://api.star-history.com/svg?repos=ssbuild/baichuan_finetuning\u0026type=Date)](https://star-history.com/#ssbuild/baichuan_finetuning\u0026Date)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssbuild%2Fbaichuan_finetuning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fssbuild%2Fbaichuan_finetuning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fssbuild%2Fbaichuan_finetuning/lists"}