twinny
code-llama-for-vscode
twinny | code-llama-for-vscode | |
---|---|---|
7 | 5 | |
1,750 | 516 | |
- | - | |
9.9 | 4.6 | |
4 days ago | 9 months ago | |
TypeScript | Python | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
twinny
- Twinny: Locally hosted (or API hosted) AI code completion for Visual Studio Code
-
The lifecycle of a code AI completion
For those who might not be aware of this, there is also an open source project on GitHub called "Twinny" which is an offline Visual Studio Code plugin equivalent to Copilot: https://github.com/rjmacarthy/twinny
It can be used with a number of local model services. Currently for my setup on a NVIDIA 4090, I'm running both the base and instruct model for deepseek-coder 6.7b using 5_K_M Quantization GGUF files (for performance) through llama.cpp "server" where the base model is for completions and the instruct model for chat interactions.
llama.cpp: https://github.com/ggerganov/llama.cpp/
deepseek-coder 6.7b base GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-base-GGU...
deepseek-coder 6.7b instruct GGUF files: https://huggingface.co/TheBloke/deepseek-coder-6.7B-instruct...
- Private Ollama GitHub Copilot Alternative with FIM and Chat
- Ollama AI code completion plugin for VSCode, 100% free and 100% private
- A new locally hosted AI code completion API and vscode extension. Like Copilot but totally free and best of all private.
- Continue with LocalAI: An alternative to GitHub's Copilot that runs locally
-
Locally hosted code completion API and vscode extension. 100% free and 100% private.
https://github.com/rjmacarthy/twinny - vscode extension https://github.com/rjmacarthy/twinny-api - python inference api
code-llama-for-vscode
-
Stable Code 3B: Coding on the Edge
How are people using codellama and this in their workflows?
I found one option: https://github.com/xNul/code-llama-for-vscode
But I'm guessing there are others, and they might differ in how they provide context to the model.
-
LLMs up to 4x Faster With latest Nvidia drivers on Windows
Do you use https://github.com/xNul/code-llama-for-vscode or something else?
Haven’t found any good setup instructions for Linux or my Google skills are failing me.
-
Continue with LocalAI: An alternative to GitHub's Copilot that runs locally
Ollama only works on Mac. Here is a portable option:
https://github.com/xnul/code-llama-for-vscode
- Code Llama for VS Code
- Code Llama for VSCode - A simple API which mocks llama.cpp to enable support for Code Llama with the Continue Visual Studio Code extension. Cross-platform support. No login/key/etc, 100% local.
What are some alternatives?
twinny-api - Locally hosted AI code completion server. Like Github Copilot but 100% free and 100% private.
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]
pinferencia - Python + Inference - Model Deployment library in Python. Simplest model inference server ever.
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
koboldcpp - A simple one-file way to run various GGML and GGUF models with KoboldAI's UI
go-llama2 - Llama 2 inference in one file of pure Go
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
Finetune_LLMs - Repo for fine-tuning Casual LLMs
aichat - All-in-one AI-Powered CLI Chat & Copilot that integrates 10+ AI platforms, including OpenAI, Azure-OpenAI, Gemini, VertexAI, Claude, Mistral, Cohere, Ollama, Ernie, Qianwen...
GoLLIE - Guideline following Large Language Model for Information Extraction
AnglE - Angle-optimized Text Embeddings | 🔥 SOTA on STS and MTEB Leaderboard
Fooocus - Focus on prompting and generating