local-llm-ops

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Local LLM Ops (Ollama)

本地LLM运维（Ollama）

Overview

概述

Your

localLLM

repo provides a full local LLM toolchain on Apple Silicon: setup scripts, a rich CLI chat launcher, benchmarks, and diagnostics. The operational path is: install Ollama, ensure the service is running, initialize the venv, pull models, then launch chat or benchmarks.

你的

localLLM

仓库为Apple Silicon提供了完整的本地LLM工具链：安装脚本、功能丰富的CLI聊天启动器、基准测试和诊断工具。操作流程为：安装Ollama，确保服务运行，初始化venv，拉取模型，然后启动聊天或基准测试。

Quick Start

快速开始

bash

./setup_chatbot.sh
./chatllm

If no models are present:

bash

ollama pull mistral

bash

./setup_chatbot.sh
./chatllm

如果没有模型，请执行：

bash

ollama pull mistral

Setup Checklist

安装配置清单

Install Ollama:
```
brew install ollama
```
Start the service:
```
brew services start ollama
```
Run setup:
```
./setup_chatbot.sh
```
Verify service:
```
curl http://localhost:11434/api/version
```

安装Ollama：
```
brew install ollama
```
启动服务：
```
brew services start ollama
```
运行安装脚本：
```
./setup_chatbot.sh
```
验证服务：
```
curl http://localhost:11434/api/version
```

Chat Launchers

聊天启动器

```
./chatllm
```
(primary launcher)
```
./chat
```
or
```
./chat.py
```
(alternate launchers)
Aliases:
```
./install_aliases.sh
```
then
```
llm
```
,
```
llm-code
```
,
```
llm-fast
```

Task modes:

bash

./chat -t coding -m codellama:70b
./chat -t creative -m llama3.1:70b
./chat -t analytical

```
./chatllm
```
（主启动器）
```
./chat
```
或
```
./chat.py
```
（备用启动器）
别名设置：执行
```
./install_aliases.sh
```
后可使用
```
llm
```
,
```
llm-code
```
,
```
llm-fast
```

任务模式示例：

bash

./chat -t coding -m codellama:70b
./chat -t creative -m llama3.1:70b
./chat -t analytical

Benchmark Workflow

基准测试流程

Benchmarks are scripted in

scripts/run_benchmarks.sh

bash

./scripts/run_benchmarks.sh

This runs

bench_ollama.py

with:

```
benchmarks/prompts.yaml
```
```
benchmarks/models.yaml
```
Multiple runs and max token limits

基准测试脚本位于

scripts/run_benchmarks.sh

：

bash

./scripts/run_benchmarks.sh

该脚本会运行

bench_ollama.py

，并使用以下资源：

```
benchmarks/prompts.yaml
```
```
benchmarks/models.yaml
```
多轮运行及最大令牌限制

Diagnostics

诊断工具

Run the built-in diagnostic script when setup fails:

bash

./diagnose.sh

Common fixes:

Re-run
```
./setup_chatbot.sh
```
Ensure
```
ollama
```
is in PATH
Pull at least one model:
```
ollama pull mistral
```

当安装配置失败时，运行内置的诊断脚本：

bash

./diagnose.sh

常见修复方案：

重新运行
```
./setup_chatbot.sh
```
确保
```
ollama
```
在系统PATH中
至少拉取一个模型：
```
ollama pull mistral
```

Operational Notes

运维注意事项

Virtualenv lives in
```
.venv
```
Chat configs and sessions live under
```
~/.localllm/
```
Ollama API runs at
```
http://localhost:11434
```

虚拟环境（virtualenv）位于
```
.venv
```
聊天配置和会话存储在
```
~/.localllm/
```
目录下
Ollama API运行地址为
```
http://localhost:11434
```

local-llm-ops

Original

Translation

Local LLM Ops (Ollama)

本地LLM运维（Ollama）

Overview

概述

Quick Start

快速开始

Setup Checklist

安装配置清单

Chat Launchers

聊天启动器

Benchmark Workflow

基准测试流程

Diagnostics

诊断工具

Operational Notes

运维注意事项

Related Skills

相关技能