install

dev 通过一下方式安装pip install -U git+https://github.com/ssbuild/deep_training.gitpip install -U transformers>=4.30 deepspeed xformers bitsandbytes>=0.39 accelerate>=0.20

weight

data sample

{"id":1,"conversations": [{"from":"system","value":"You are ChatGLM4, a large language model trained by Zhipu.AI. Follow the user's instructions carefully. Respond using markdown."}, {"from":"user","value":"Hello"}, {"from":"assistant","value":"Hello, I'm ChatGLM4. What can I assist you today?"}]}{"id": 2, "conversations": [{"from": "system", "value": "你是一个名为 GLM-4 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。", "tools": "[\n  {\n    \"type\": \"function\",\n    \"function\": {\n      \"name\": \"get_current_weather\",\n      \"description\": \"Get the current weather in a given location\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"location\": {\n            \"type\": \"string\",\n            \"description\": \"The city and state, e.g. San Francisco, CA\"\n          },\n          \"unit\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"location\"\n        ]\n      }\n    }\n  }\n]"}, {"from": "user", "value": "今天北京的天气怎么样？"}, {"from": "assistant", "value": "{\"name\": \"get_current_weather\", \"arguments\": {\"location\": \"beijing\", unit=\"celsius\"}}\n"}, {"from": "observation", "value": "{\"temperature\": 22}"}, {"from": "assistant", "value": "根据查询结果，今天北京的气温为 22 摄氏度。"}]}{"id": 3, "conversations": [{"from": "system", "value": "你是一个名为 GLM-4 的人工智能助手。你是基于智谱AI训练的语言模型 GLM-4 模型开发的，你的任务是针对用户的问题和要求提供适当的答复和支持。", "tools": "[\n  {\n    \"type\": \"function\",\n    \"function\": {\n      \"name\": \"get_recommended_books\",\n      \"description\": \"Get recommended books based on user's interests\",\n      \"parameters\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"interests\": {\n            \"type\": \"array\",\n            \"items\": {\n              \"type\": \"string\"\n            },\n            \"description\": \"The interests to recommend books for\"\n          }\n        },\n        \"required\": [\n          \"interests\"\n        ]\n      }\n    }\n  }\n]"}, {"from": "user", "value": "Hi, I am looking for some book recommendations. I am interested in history and science fiction."}, {"from": "assistant", "value": "{\"name\": \"get_recommended_books\", \"arguments\": {\"interests\": [\"history\", \"science fiction\"]}}\n"}, {"from": "observation", "value": "{\"books\": [\"Sapiens: A Brief History of Humankind by Yuval Noah Harari\", \"A Brief History of Time by Stephen Hawking\", \"Dune by Frank Herbert\", \"The Martian by Andy Weir\"]}"}, {"from": "assistant", "value": "Based on your interests in history and science fiction, I would recommend the following books: \"Sapiens: A Brief History of Humankind\" by Yuval Noah Harari, \"A Brief History of Time\" by Stephen Hawking, \"Dune\" by Frank Herbert, and \"The Martian\" by Andy Weir."}]}{"id":4,"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。"}]}{"id": 5, "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。"}]}

infer

# infer.py 推理预训练模型# infer_finetuning.py 推理微调模型# infer_lora_finetuning.py 推理lora微调模型 python infer.py

training

# 制作数据cd scriptsbash train_full.sh -m dataset orbash train_lora.sh -m dataset orbash train_ptv2.sh -m dataset 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dataHelper.make_dataset_with_args(data_args.train_file,mixed_data=False, shuffle=True,mode='train',num_process_worker=0)# 全参数训练     bash train_full.sh -m train     # lora adalora ia3     bash train_lora.sh -m train     # ptv2    bash train_ptv2.sh -m train

训练参数

友情链接

纯粹而干净的代码

Reference

https://huggingface.co/THUDM/glm4

Star History