对qwen2.5进行微调以及知识蒸馏
☆17Dec 24, 2024Updated last year
Alternatives and similar repositories for qwen2.5_sft_kd
Users that are interested in qwen2.5_sft_kd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 基于电商数据微调的Qwen2.5系列的电商大模型,电商数据sft后电商大模型。是https://github.com/leeguandong/EcommerceLLM的升级版本。qwen2.5的效果很好。☆14Oct 4, 2024Updated 2 years ago
- 基于cnn的视频动作分类教程。☆11Aug 17, 2020Updated 6 years ago
- A lightweight SGLang implementation built from scratch.☆12Jul 29, 2025Updated last year
- python人脸识别和情绪识别☆17Oct 2, 2023Updated 3 years ago
- SwornDisk是一个面向可信执行环境的、基于日志结构的安全块设备(全国大学生操作系统比赛2022)☆24Aug 14, 2022Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ☆19Nov 10, 2024Updated last year
- CUDA SGEMM optimization note☆16Oct 31, 2023Updated 2 years ago
- skills大全,收集/分类/整理现有的skills,旨在提高每个skill的利用效率。欢迎所有人贡献和交流。Mail:connect@chuchiangdata.cc☆20May 6, 2026Updated 5 months ago
- 本项目是一款基于 Python 与 AI 大语言模型的财经新闻智能分析工具,能够自动从财经资讯网站抓取最新新闻,提取标题与正文,并调用 AI 模型对新闻进行行业归类、关键词提炼、市场影响评估及事件关联分析。系统可批量处理新闻,输出结构化分析结果至 pdf文件以及自动发送研报…☆24Aug 13, 2025Updated last year