Overview

This document is a list of blog posts from the website “九原山.” The blog posts cover various topics such as evaluation and fine-tuning of embedding models in the RAG scenario, implementing a blog based on Github Issues, learning paths and resources for large language models (LLM), evaluation results of Chinese models, training data preparation for LLM, open-source models with good Chinese support, micro-tuning techniques for LLM, a tool for fast distribution of large files on an internal network, modifying game saves for “Plants vs. Zombies” on PC/Mac, implementing physical queues in Kubernetes based on namespaces, SRE technical briefings, the game “天命奇御,” and recommendations from SREcon18 Americas.

Features

• Embedding Model Evaluation and Fine-tuning in RAG Scenario
• Implementation of Blog Based on Github Issues
• Learning Paths and Resources for Large Language Models (LLM)
• Evaluation Results of Chinese Models
• Training Data Preparation for LLM
• Open-source Models with Good Chinese Support
• Micro-tuning Techniques for LLM
• p2pfile - Tool for Fast Distribution of Large Files on an Internal Network
• Modifying Game Saves for “Plants vs. Zombies” on PC/Mac
• Implementing Physical Queues in Kubernetes Based on Namespaces
• SRE Technical Briefings
• Game “天命奇御”
• Recommendations from SREcon18 Americas

Installation

The installation steps for the themes discussed in the blog posts are not provided in the content.

Summary

The document is a collection of blog post titles from the website “九原山.” The blog posts cover a variety of topics including language models, evaluation, fine-tuning, implementation of blogs, game modifications, and SRE technical briefings. Unfortunately, no detailed information or analysis is given for each blog post.