基于Qwen3-VL-8B模型的数据构建/微调/强化学习/Agentic RAG项目
☆18May 26, 2026Updated 5 months ago
Alternatives and similar repositories for vlm-posttraining-ecommerce
Users that are interested in vlm-posttraining-ecommerce 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 DeepTutor 理念重构的个人专属 AI 导师 Agent。本项目完全抛弃了原有的执行框架，底层采用 LangChain 与 LangGraph 进行彻底重写。通过构建基于图（Graph）的认知工作流与健壮的状态管理（State Management），实现了更具…☆16Updated this week
- The implementation of Teachability-Aware On-Policy Distillation (TA-OPD), the method introduced in Not All Disagreement Is Learnable: Tok…☆21May 25, 2026Updated 5 months ago
- ☆23Jun 3, 2026Updated 4 months ago
- This repository includes code for our paper: ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning…☆17May 2, 2026Updated 5 months ago
- AI, Azure, Philosophy & Engineering musings — an Obsidian-powered digital forge for deep thinking☆28Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 动手训练一个简单的Llava模型。☆12Apr 23, 2025Updated last year
- Official codebase for CaptionFormer : Unified Segmentation, Tracking, and Captioning for Spatio-Temporal Objects [CVPR26]☆22Jun 20, 2026Updated 4 months ago
- ☆29Sep 7, 2026Updated last month
- langchain + chatglm + rag >text2sql☆10Jul 21, 2024Updated 2 years ago
- ☆31Jul 31, 2026Updated 3 months ago
- An RL environment similar to Cognition's SWE-Grep☆17Mar 10, 2026Updated 7 months ago
- 基于qwen3的医疗大模型研发全流程 0.分词训练 1.增量预训练 2.微调 3.强化 4.量化 5.蒸馏 6.评估 7.lora模型合并 8.服务 9.部署☆57Jan 3, 2026Updated 9 months ago
- [ICML 2026] Hybrid Policy Distillation (HPD) is a practical distillation framework for reasoning-oriented language models. This repositor…☆24Apr 24, 2026Updated 6 months ago
- 一个基于保险QA以及合同条款的RAG业务链,使用了Qwen的api作为语言模型,其中还包括了分类算法(意图识别)的训练, RAG embedding模型的微调, 稠密稀疏indexing的建立和混合使用☆12Jun 12, 2024Updated 2 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- 60天AI质量保障实战训练营 - 从测试工程师视角系统掌握LLM测试方法论 涵盖：温度参数验证、Prompt注入防御、RAG评估、Agent自动化测试等企业级实战内容☆24Aug 18, 2026Updated 2 months ago
- [NeurIPS 2026] Agentic reinforcement learning for CLI agents with structured action credit assignment, budgeted workspace context selecti…☆19Oct 12, 2026Updated 2 weeks ago
- 卷积神经网络，多位数字识别，这个一个用于学生考试试卷分数核对矫正的应用☆13May 1, 2023Updated 3 years ago
- 🎙️ CosyVoice LoRA 微调框架：LLM+Flow 联合训练，实现无 Prompt 语音合成☆14Jan 5, 2026Updated 9 months ago
- 本项目由三个模块构成。意图识别：判断用户的意图是业务型还是闲聊型；模型检索：该部分构建一个语料库，当用户 发起新的query（通过意图识别判断为业务型对话）时，为用户匹配query检索的最佳response，使用HSWN进行召回（粗排）， 然后构建句子的相似度，并利用Lig…☆12Feb 18, 2021Updated 5 years ago
- Official implementation of "Learning To Draft: Adaptive Speculative Decoding with Reinforcement Learning" (ICLR 2026)☆24Mar 1, 2026Updated 7 months ago
- SkyCompass（天空罗盘） 是一个运行在 M5Stack CardputerADV 上的天体导航应用，通过Cap LoRa-1262模块中的GNSS获取定位，用于可视化太阳、月亮和银河在天空中的运行轨迹、天文潮汐计算。支持六轴传 感器控制观察视角。☆21Aug 13, 2026Updated 2 months ago
- 本项目是一个完整的轮腿机器人（Wheel-Legged Robot）控制和仿真系统，基于ROS2框架开发。项目包含两款机器人平台：cyclBot和 seriBot ，支持实时硬件控制、MuJoCo仿真、动力学建模和高级控制算法。☆21Apr 14, 2026Updated 6 months ago
- Museum-AI 是一个面向博物馆工作者和文物研究人员的智能知识管理与对话系统。项目基于多模态知识库架构（LangGraph + LangChain），通过向量检索、知识图谱和智能体技术，帮助用户高效管理文物知识、构建专业知识库，并进行智能问答。Museum-AI 支持 …☆24May 23, 2026Updated 5 months ago
- 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.
- Collection for Zotero：用 LLM根据「标题 + 摘要」为条目智能推荐 Zotero 分类，并提供可审核的确认对话框。☆29Aug 25, 2026Updated 2 months ago
- 一些用于互联网算法岗面试复习用的常见手撕代码合集：排序算法、最短路算法、二叉树遍历算法、sql语句、nms算法、IOU算法、多头注意力MHA等☆23Mar 18, 2025Updated last year
- 政策新闻领域 实体识别+关系抽取 基于4000句txt微调得到☆14Aug 11, 2026Updated 2 months ago
- 基于mobilev2和YOLOv3的目标检测的android端的ncnn的实现☆10Mar 20, 2020Updated 6 years ago
- Log☆11Nov 8, 2021Updated 4 years ago
- RGBD相机调研☆12Aug 25, 2019Updated 7 years ago
- 基于ROS框架的 Ikid Robot 仿人足球机器人项目。功能包包括 gazebo仿真环境、机器人运动控制、步态调试服务端等。☆12Dec 10, 2023Updated 2 years ago
- github for the code agent☆19Dec 11, 2025Updated 10 months ago
- 基于 Microsoft Qlib 扩展的六大因子库，专为中国A股市场优化的量化因子工程。含 Alpha360/158/101、GTJA191、TDXGS、JQ110 共 1000+ 因子☆18Jul 17, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- BTC 实时交易信号系统，结合订单流、多因子共振分析与机器学习模型。BTC real-time trading signal system, combining order flow, multi-factor resonance analysis and machine …☆12Feb 22, 2026Updated 8 months ago
- 通用选股策略 Skill，面向 AI Agent 的可解释多因子选股工作流☆12Jul 30, 2026Updated 3 months ago
- ☆17May 14, 2026Updated 5 months ago
- Daily Reporter Skill —— 职场汇报智能生成助手，将碎片化工作记录自动转化为专业的日报/周报/月报☆27Apr 14, 2026Updated 6 months ago
- Binance 永续合约 1 分钟数据 + 资金费率的短周期（5/15/30 分钟）预测研究，含改进 CTA 情绪因子与强化学习示例环境 | Short-horizon prediction on BTC perpetuals from 1-minute data and …☆14Mar 31, 2025Updated last year
- Quant Autoresearch is an autonomous framework for trading strategy evolution, adapted from the Karpathy's `autoresearch` philosophy. It t…☆14Mar 18, 2026Updated 7 months ago
- 让 Coding Agent 精准 Pin 到正确代码：基于 Agentic RL 后训练，定位文件、类与函数级上下文。☆22Sep 6, 2026Updated last month