xNul / code-llama-for-vscode
Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.
β557Updated 5 months ago
Alternatives and similar repositories for code-llama-for-vscode:
Users that are interested in code-llama-for-vscode are comparing it to the libraries listed below
- C++ implementation for π«StarCoderβ449Updated last year
- LLM powered development for VSCodeβ1,254Updated 6 months ago
- Tune any FALCON in 4-bitβ466Updated last year
- Visual Studio Code extension for WizardCoderβ145Updated last year
- starcoder server for huggingface-vscdoe custom endpointβ168Updated last year
- β1,025Updated last year
- INT4/INT5/INT8 and FP16 inference on CPU for RWKV language modelβ1,449Updated 5 months ago
- β536Updated last year
- Supercharge Open-Source AI Modelsβ350Updated last year
- β1,443Updated last year
- Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internetβ688Updated last year
- Falcon LLM ggml framework with CPU and GPU supportβ245Updated 11 months ago
- Customizable implementation of the self-instruct paper.β1,035Updated 10 months ago
- Llama 2 Everywhere (L2E)β1,508Updated this week
- fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backeβ¦β409Updated last year
- Self-evaluating interview for AI codersβ552Updated last week
- β203Updated 4 months ago
- ggml implementation of BERTβ474Updated 10 months ago
- β168Updated last year
- TheBloke's Dockerfilesβ300Updated 10 months ago
- Large-scale LLM inference engineβ1,235Updated this week
- Octogen is an Open-Source Code Interpreter Agent Frameworkβ255Updated 5 months ago
- WebUI for Fine-Tuning and Self-hosting of Open-Source Large Language Models for Codingβ1,642Updated this week
- Python bindings for the Transformer models implemented in C/C++ using GGML library.β1,827Updated 11 months ago
- β704Updated 10 months ago
- A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformerβ1,626Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantizationβ448Updated 9 months ago
- LLaMa retrieval plugin script using OpenAI's retrieval pluginβ324Updated last year
- β413Updated last year
- An easy way to host your own AI API and expose alternative models, while being compatible with "open" AI clients.β328Updated 6 months ago