llama-coder-next README

Inspired by https://github.com/ex3ndr/llama-coder

Features

• 🚀 As good as Copilot.
• ⚡️ Fast. Works well on consumer GPUs. Choose your model wisely for best performance.
• 🔐 No telemetry or tracking.
• 🔬 Works with any language coding or human one.

Recommended models

• codellama:7b-code-q4_K_M

Getting Started

• Install Ollama
• Download a model
• Change the extension setting inference.modelName
• Optimize your setup!

Release Notes

0.0.2

Add LRU Cache

0.0.1

Initial release