joreilly86/ engineering_assistant_3.0:latest

211 1 year ago

Fine tuned as a multi-agent assistant for civil/structural engineering tasks. 

ollama run joreilly86/engineering_assistant_3.0

Details

1 year ago

5bafef5d112d · 4.7GB ·

model
llama
·
8.03B
·
Q4_0
license
META LLAMA 3 COMMUNITY LICENSE AGREEMENT Meta Llama 3 Version Release Date: April 18, 2024 “Agreem
system
Initiate General Engineering Assistance Mode: As the Central Intelligence (CI), your primary functio
params
{ "num_keep": 24, "stop": [ "<|start_header_id|>", "<|end_header_id|>",
template
{{ if .System }}<|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }}{{ if .Pr

Readme

General Engineering Assistant 🤖🏗

Overview

The General Engineering Assistant is an AI tool designed to support a wide range of engineering tasks. Leveraging the power of the Llama 3 instruction-tuned model, this assistant provides comprehensive support across administrative, civil, structural, geotechnical, and mechanical engineering domains.

The model uses specialized expert agents to provide targeted support across administrative, civil, structural, geotechnical, and mechanical engineering tasks, leveraging their distinct competencies and collaborative problem-solving capabilities to provide comprehensive, accurate, and efficient solutions tailored to the user’s specific engineering challenges.

This is a work in progress that I am continuously tuning.

Features

  • Administrative and Research Support: Project management, documentation, literature reviews, and data analysis.
  • Civil and Structural Engineering: Structural analysis, design, and construction planning.
  • Geotechnical and Mechanical Engineering: Soil analysis, foundation design, mechanical systems, and material properties.

Getting Started

Prerequisites

  • Docker: Ensure Docker is installed on your machine.
  • OpenWebUI: Recommended for running local Llama models.

Installation

  1. Pull the Model

    ollama pull joreilly86/structural_llama_3.0

  2. Install OpenWebUI Using Docker

    docker pull openwebui/openwebui:latest
docker run -p 8080:8080 openwebui/openwebui:latest

  3. Run the Model with OpenWebUI

    • Access OpenWebUI in your web browser at http://localhost:8080 and configure it to use the structural_llama_3.0 model.

Usage

Running the Model

Interact with the model using:

ollama run joreilly86/structural_llama_3.0 "Your question or instruction here"

Examples

  • Technical Guidance:

    ollama run joreilly86/structural_llama_3.0 "Explain the factors affecting the stability of a cantilever beam."

  • Code Generation:

    ollama run joreilly86/structural_llama_3.0 "Generate a Python function to calculate the bending moment of a simply supported beam."

Support

For issues and support, check out the Ollama Documentation. For Python for Engineering stuff, visit flocode.dev.