Gaia Node Configurations

This repository contains a collection of pre-set configuration files for quickly starting Gaia nodes with various large language models (LLMs) and settings. These configurations aim to simplify the process of deploying and using Gaia nodes for different use cases.

‼️ The pre-set configuration files only support Gaia node version 0.5.0 and above. If your node version is below 0.5.0, please remove the llamaedge_chat_port and llamaedge_embedding_port parameters.

Pre-set Configurations

You can find configuration files for the following models and their setup instructions in their respective readmes.

🧠 Language models

• codegemma-7b-it

• codestral-0.1-22b

• deepseek-2.5-236b

• deepseek-r1-distill-llama-70b

• deepseek-r1-distill-llama-8b

• diplo

• exaone-3.5-2.4b-instruct

• exaone-3.5-32b-instruct

• exaone-3.5-7.8b-instruct

• exaone-deep-2.4b

• exaone-deep-32b

• exaone-deep-7.8b

• gemma-1.1-7b-it

• gemma-2-27b-it

• gemma-2-9b-it

• gemma-3-1b-it

• gemma-3-4b-it

• gemma-3-12b-it

• gemma-3-27b-it

• llama-2-7b

• llama-3-70b-instruct

• llama-3-8b-instruct

• llama-3-8b-instruct-262k

• llama-3-8b-instruct_london

• llama-3-8b-instruct_paris

• llama-3-Korean-Blossom-8B

• llama-3-groq-8b-tool

• llama-3.1-70b-instruct

• llama-3.1-8b-instruct

• llama-3.1-8b-instruct_basechain

• llama-3.1-8b-instruct_chemistry

• llama-3.1-8b-instruct_pastor

• llama-3.1-8b-instruct_rustlang

• llama-3.1-8b-instruct_samsung-s24

• llama-3.1-nemotron-70b-instruct

• llama-3.2-1b-instruct

• llama-3.2-3b-instruct

• llama-3.2-3b-instruct_paris

• llama-3.3-70b-instruct

• llama-4-scout-17b-16e-instruct

• mathstral-7b

• mistral-0.3-7b-instruct

• mistral-0.3-7b-instruct-tool-call

• mistral-small-24b-instruct

• openchat

• phi-3-medium-instruct-128k

• phi-3-medium-instruct-4k

• phi-3-mini-instruct-128k

• phi-3-mini-instruct-128k_london

• phi-3-mini-instruct-128k_paris

• phi-3-mini-instruct-4k

• phi-3-mini-instruct-4k_gaianet

• phi-3.5-mini-instruct

• qwen-1.5-0.5b-chat

• qwen-1.5-1.8b-chat

• qwen-1.5-4b-chat

• qwen-1.5-7b-chat

• qwen-2.5-coder-0.5b-instruct

• qwen-2.5-coder-1.5b-instruct

• qwen-2.5-coder-14b-instruct

• qwen-2.5-coder-14b-instruct_rustlang

• qwen-2.5-coder-32b-instruct

• qwen-2.5-coder-32b-instruct_rustlang

• qwen-2.5-coder-3b-instruct-gte

• qwen-2.5-coder-3b-instruct

• qwen-2.5-coder-7b-instruct

• qwen-2.5-coder-7b-instruct_aelf

• qwen-2.5-coder-7b-instruct_rustlang

• qwen2-0.5b-instruct

• qwen2-0.5b-instruct_rustlang

• qwen2-1.5b-instruct

• qwen2-32b-instruct

• qwen2-72b-instruct

• qwen2-7b-instruct

• qwen2.5-0.5b-instruct

• qwen2.5-1.5b-instruct

• qwen2.5-14b-instruct

• qwen2.5-32b-instruct

• qwen2.5-3b-instruct

• qwen2.5-70b-instruct

• qwen2.5-7b-instruct

• qwq-32b

• reflection-llama-3.1-70b-instruct

• stablelm-2-zephyr-1.6b

• vitalik.eth-7b-chat_vitalik-blog

• yi-1.5-34b-chat-16k

• yi-1.5-9b-chat

• yi-coder-1.5b-chat

• yi-coder-1.5b

• yi-coder-9b-chat

• yi-coder-9b-chat_rustlang

• Specialized Knowledge Bases:

  • London tour guide
  • Paris tour guide
  • Rust programming language documentation
  • Base blockchain documentation
  • Chemistry knowledge
  • Bible teachings
  • Vitalik Buterin's writings

  ... and many more.

Quick Start

Most configurations follow a similar quick start guide:

1. Install Gaia node:

   curl -sSfL https://github.com/GaiaNet-AI/gaianet-node/releases/latest/download/install.sh | bash
   

2. Initialize with a pre-set configuration: Replace the example URL with the specific config.json URL from this repository. For example:

   gaianet init --config https://raw.githubusercontent.com/GaiaNet-AI/node-configs/main/llama-3-8b-instruct/config.json
   

3. Start the node:

   gaianet start
   

After starting, you can usually access your Gaia node as a web-based chatbot or as an OpenAI API drop-in replacement. Refer to the Gaia documentation for more detailed usage instructions.

References

• Gaia Documentation
• Gaia Node GitHub Repository
• LlamaEdge GitHub Repository
• Model-specific references are often included in the individual configuration README.md files.

License

This work is licensed under the Apache License 2.0.