通过lora对deepseek小模型进行微调
☆22Nov 15, 2024Updated last year
Alternatives and similar repositories for deepseek-fine-tuning
Users that are interested in deepseek-fine-tuning are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 本项目从零开始构建并优化了一个千万参数级别的大规模预训练语言模型，涵盖预训练、有监督微调（SFT）和R1推理蒸馏三个阶段。项目采用自定义Transformer架构（包括RMSNorm、分组注意力、多Query机制、SwiGLU激活和RoPE位置编码），实现高效的长文本处理和…☆22Mar 10, 2025Updated last year
- ☆10Apr 30, 2025Updated last year
- 人岗匹配模型，采用 dssm方法和deepffm实现☆11Jul 26, 2019Updated 6 years ago
- 标注自己的数据集，训练、评估、测试、部署自己的人工智能算法☆11May 28, 2024Updated 2 years ago
- 使用大模型自动构建课程知识图谱☆10Aug 9, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆13Feb 3, 2022Updated 4 years ago
- 数据治理整体架构☆10Nov 11, 2019Updated 6 years ago
- 小芭智能简历解析系统☆16Apr 11, 2023Updated 3 years ago
- 大数据/机器学习可视化分析平台☆11Dec 11, 2019Updated 6 years ago
- Code for paper "PoseEmbroider:Towards a 3D, Visual, Semantic-aware Human Pose Representation" (ECCV 2024)☆18Nov 18, 2024Updated last year
- ☆12May 19, 2021Updated 5 years ago
- A Modular Pytorch ViTGAN implementation☆12Mar 15, 2022Updated 4 years ago
- 使用keras实现GhostNet☆15May 24, 2020Updated 6 years ago
- 爱淘优惠券☆11Sep 14, 2020Updated 5 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆10Mar 21, 2023Updated 3 years ago
- 完成了《实战Google深度学习框架》里的内容☆20Oct 6, 2018Updated 7 years ago
- 运维云平台之服务树☆13Aug 7, 2017Updated 8 years ago
- colab list for image☆19Apr 15, 2026Updated 2 months ago
- A web application where clients can book appointment for lawyers.☆12Feb 29, 2024Updated 2 years ago
- 人岗精准匹配模型☆19Aug 5, 2021Updated 4 years ago
- This project aims at adjusting the VideoPose3D project from Dario Pavllo, in order to track the trajectories of multiple people and predi…☆10Mar 28, 2021Updated 5 years ago
- 微信抢红包，支持后台通知和聊天界面抢红包☆13Mar 8, 2017Updated 9 years ago
- 🚀 SparkX 是采用 Springboot3 开发的 基于大语言模型和编排的企业智能体开发平台。开箱即用、模型中立、灵活编排，支持快速嵌入到第三方业务系统。☆37Jul 31, 2025Updated 10 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- claude CLI（cc）客户端工具，使用可视化方式进行环境和模型对话管理☆36Oct 12, 2025Updated 8 months ago
- Client library for the Fourier GRx series robot☆16May 16, 2025Updated last year
- 一个python版flask web项目,同时也对接了CAS单点登录,简单集成chatterbot和qqbot的智能聊天机器人。☆14May 4, 2017Updated 9 years ago
- the code of our paper "Beyond Matching: Modeling Two-Sided Multi-Behavioral Sequences For Dynamic Person-Job Fit" (实现十多个人岗匹配模型和动态人岗匹配模型的算…☆16Aug 10, 2023Updated 2 years ago
- 使用vis.js可视化知识图谱，使用Flask框架，数据库为neo4j，实现查询节点，显示节点的知识图谱导力图☆15Mar 2, 2023Updated 3 years ago
- A template engine for LLM prompts with support for writing prompts with prompts☆23Mar 31, 2025Updated last year
- Variational Autoencoder-Generative Adversarial Network (VAE-GAN) to hide data inside images☆12Nov 9, 2019Updated 6 years ago
- Import Facebook events into Neo4j using Flask and visualize with D3☆23Sep 2, 2023Updated 2 years ago
- Subpixel phase correlation for image registration, adapted for Pytorch API with GPU support☆14Nov 4, 2020Updated 5 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- 使用FastAPI+vLLM部署Qwen2.5☆25Sep 29, 2024Updated last year
- Dsxquant 是一个基于python语言开发的的量化工具箱，主要特征是其工具属性，专为上层策略应用提供服务。☆14Mar 31, 2025Updated last year
- 基于DeepSeek模型的本地部署方案 能够处理并索引多种格式的本地文档（PDF、Word、Excel、TXT、HTML等） 支持约5000+份私有文档的高效检索与分析 具备互联网搜索能力，实现本地数据与网络数据的融合分析 提供数据分析、预测功能 提供本地知识库问答功能☆19Dec 4, 2025Updated 6 months ago
- Claude Code skill for using Codex CLI as an execution specialist for implementation-heavy coding work, multi-file refactors, and wrapper-…☆59May 21, 2026Updated 3 weeks ago
- ☆17Apr 1, 2024Updated 2 years ago
- SVM and CNN experiment on Fashion MNIST dataset using sklearn and pytorch.☆13Dec 15, 2019Updated 6 years ago
- 🛰️ 基于真实医疗对话数据在ChatGLM上进行LoRA、P-Tuning V2、Freeze、RLHF等微调，我们的眼光不止于医疗问答☆338Sep 2, 2023Updated 2 years ago