Text Generation
PEFT
Chinese
English
preference-learning
qlora
agent
personalization
association-engine
Instructions to use feiertu/hermes-association-engine with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use feiertu/hermes-association-engine with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
| # Hermes 联想引擎 Docker 镜像 | |
| # 构建: docker build -t hermes . | |
| # 运行: docker run -d -v hermes_data:/root/.hermes --name hermes hermes | |
| FROM python:3.11-slim | |
| LABEL org.opencontainers.image.title="Hermes" | |
| LABEL org.opencontainers.image.description="Agent 偏好学习与联想引擎" | |
| # 安装系统依赖 | |
| RUN apt-get update && apt-get install -y --no-install-recommends \ | |
| curl \ | |
| && rm -rf /var/lib/apt/lists/* | |
| # 设置工作目录 | |
| WORKDIR /app | |
| # 安装 Python 依赖 | |
| COPY pyproject.toml . | |
| RUN pip install --no-cache-dir -e ".[train]" 2>/dev/null || \ | |
| pip install --no-cache-dir click sentence-transformers numpy | |
| # 复制源码 | |
| COPY hermes_core/ hermes_core/ | |
| COPY cli/ cli/ | |
| COPY daemon/ daemon/ | |
| # 安装 | |
| RUN pip install -e . | |
| # 预下载 embedding 模型 | |
| RUN python -c "from hermes_core.embedder import Embedder; Embedder()" 2>/dev/null || true | |
| # 数据卷 | |
| VOLUME /root/.hermes | |
| # 默认启动 daemon | |
| CMD ["hermes", "daemon", "--foreground"] | |