microPost: Coding Models at Ollama.

Or: Listing the Tools for Automated Code Generation.

UpdatedJanuary 16, 2024

Thank you for reading this post.

My name is Brian and I'm a developer from New Zealand. I've been interested in computers since the early 1990s. My first language was QBASIC. (Things have changed since the days of MS-DOS.)

I am the managing director of a one-man startup called Digital Core (NZ) Limited. I have accepted the "12 Startups in 12 Months" challenge so that DigitalCore will have income-generating products by April 2024.

This blog will follow the "12 Startups" project during its design, development, and deployment, cover the Agile principles and the DevOps philosophy that is used by the "12 Startups" project, and delve into the world of AI, machine learning, deep learning, prompt engineering, and large language models.

I hope you enjoyed this post and, if you did, I encourage you to explore some others I've written. And remember: The best technologies bring people together.

Comments

Join the discussion

No comments yet. Be the first to comment.

The Ops Series

Part 24 of 48

In the Ops series, I describe the server "operations" I use for app development and technology evaluations.

Up next

microPost: Why Devs Should Blog in 2024.

Or: Sharing My Stuff with the World.

More from this blog

System Tools for Ubuntu Desktop.

Or: Installing the Apps that Matter to Me.

Jul 9, 202629 min read17

Installing vLLM onto EVO-X2.

Or: Adding Tool Support for Local LLMs.

Jul 9, 202612 min read15

Installing ROCm & Llama.cpp for CPUs & APUs.

Or: Adding a Device Driver for AMD GPUs & iGPUs.

Jul 9, 20269 min read26

Installing ROCm & Llama.cpp for CPUs & APUs.

Installing Ruby & VS Code

Or: Adding PDF Support for AsciiDoc Files.

Jul 8, 20264 min read3

Running Hermes Agent in YOLO Mode.

Or: Going to Bed while the AI Continues to Crunch.

Jul 8, 20264 min read85

SoloDev.app

97 posts

My name is Brian, I'm from New Zealand, and I like SysOps. In 2025, I will use reasoning language models to build apps. Join me as I also explore machine learning, deep learning, Mojo, Max, and AI.

This is a μPost (microPost) lists the coding models, available from Ollama.ai, that I will evaluate in 2024 as I look to define a Full Stack App Development Process.

Install Command	Description	License
`ollama run codellama`	7B: A large language model that can use text prompts to generate and discuss code.	Llama 2 Community License Agreement.
`ollama run wizardcoder`	13B: Llama-based code generation model focused on Python.	Llama 2 Community License Agreement.
`ollama run codeup`	13B: Great code generation model based on Llama2.	Llama 2 Community License Agreement.
`ollama run open-orca-platypus2`	13B: Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.	Llama 2 Community License Agreement.
`ollama run phind-codellama`	34B: Code generation model based on CodeLlama.	Llama 2 Community License Agreement.
`ollama run codebooga`	34B: A high-performing code instruct model created by merging two existing code models.	Llama 2 Community License Agreement.
.
`ollama run dolphin-mistral`	7B: The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.6.	Apache License 2.0.
`ollama run openhermes2.5-mistral`	7B: OpenHermes 2.5 Mistral is a Mistral 7B fine-tune, a continuation of OpenHermes 2 model, which trained on additional code datasets.	Apache License 2.0.
`ollama run sqlcoder`	15B: SQLCoder is a code completion model fined-tuned on StarCoder for SQL generation tasks.	Apache License 2.0.
`ollama run starcoder`	15.5B: StarCoder is a code generation model trained on 80+ programming languages.	Apache License 2.0.
`ollama run dolphin-mixtral`	56B: An uncensored, fine-tuned model based on the Mixtral mixture of experts model that excels at coding tasks. Created by Eric Hartford.	Apache License 2.0.
`ollama run deepseek-coder`	6.7B: DeepSeek Coder is trained from scratch on both 87% code and 13% natural language in English and Chinese. Each of the models are pre-trained on 2 trillion tokens.	MIT License.
`ollama run magicoder`	7B: The Magicoder is a family of models trained on 75K synthetic instruction data using OSS-Instruct, a novel approach to enlightening LLMs with open-source code snippets.	MIT License.

Ollama.ai also hosts chat models, medical models, and others.

Command Palette

Comments

The Ops Series

microPost: Why Devs Should Blog in 2024.

More from this blog