base on Phi3 中文仓库 # phi3-Chinese phi3以小搏大（从微软放出的跑分数据看），用不到1/2的小体积（3.8b）超越llama3 8b版性能表现，增大了在手机上部署的可行性。 该仓库致力于收录分散在开源社区的各种phi3的训练变体版本，让更多网友发现那些不为人知的特色有趣权重。 同时也会顺便整理phi相关训练、推理、部署的简单教程。 ## Chat模型下载 ### Phi-3-chinese - Phi-3-mini-128k-instruct-Chinese - 增量SFT版本： - modelscope: https://modelscope.cn/models/baicai003/Phi-3-mini-128k-instruct-Chinese/summary - 直接DPO版本：https://modelscope.cn/models/zhuangxialie/Phi-3-Chinese-ORPO/summary - 扩充词表版本：计划中 ### Hugging Face（英文原版） - Phi-3-mini-128k-instruct：https://huggingface.co/microsoft/Phi-3-mini-128k-instruct - Phi-3-mini-4k-instruct：https://huggingface.co/microsoft/Phi-3-mini-4k-instruct ### ModelScope（英文原版） - Phi-3-mini-128k-instruct：https://modelscope.cn/models/LLM-Research/Phi-3-mini-128k-instruct/summary - Phi-3-mini-4k-instruct：https://modelscope.cn/models/LLM-Research/Phi-3-mini-4k-instruct/summary ## 网页部署 ``` streamlit run deploy/streamlit_for_instruct.py ./Phi-3-mini-128k-instruct-Chinese ``` <img width="1422" alt="image" src="https://github.com/CrazyBoyM/phi3-Chinese/assets/35400185/f77754e7-016b-4a66-9d8c-3e493faa11cb"> ## 当前问题 - 效果与跑分不符：理想是丰满的，但我实际深度体验英文原版、以及训练中文版体验后，发现phi3-mini并没有它说的那么好用，也许它有很大的刷分嫌疑？也许对它进行叠加block操作后很有潜力？ - 32K词表过小：它的词表太小了，而且没什么中文token，经常约用3～5个token表示一个汉字，导致虽然它的体积小、加载快、运行快，但实际吐字速度比llama3 8b版还慢。也许应该对它进行词表扩充和增量预训练？ 总体来说，我目前对它跑分超越llama3 8b的phi3-mini 3.8b版本是比较失望的， 当然也许这个版本适合更轻量级的下游垂直任务，我们不应该以gpt3.5的水平对它抱以期待？或许做个moe版本会更好？ ", Assign "at most 3 tags" to the expected json: {"id":"9687","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"