copilot.el
llama.cpp
| copilot.el | llama.cpp | |
|---|---|---|
| 20 | 773 | |
| 1,641 | 56,891 | |
| 3.2% | - | |
| 8.4 | 10.0 | |
| 17 days ago | 5 days ago | |
| Emacs Lisp | C++ | |
| 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.
copilot.el
-
Emacs-copilot: Large language model code completion for Emacs
Yeah and there's already a well-known (at least I already knew about it) package started in 2022 called "copilot" for Emacs that is actually a client for GitHub Copilot: https://github.com/zerolfx/copilot.el
Given the lack of namespacing in Elisp (or, rather, the informal namespacing conventions by which these two packages collide) it's unfortunate that this package chose the same name.
- Copilot for emacs?
-
Starhugger.el now displays suggestions as overlays
It's a package to integrate Bigcode/Starcoder into Emacs like https://github.com/zerolfx/copilot.el does with Github Copilot.
-
Bigcode/Starcoder integration
It's not fancy with previewable overlays and stuffs as https://github.com/zerolfx/copilot.el and I am not so sure if the performance is optimal, but it gets the bare job done.
-
Is there a package or something for code completion in org mode files for src blocks?
Unfortunately, the only way I've managed to get code completion working without having to use the C-c ' buffer is through the unofficial copilot.el. The good news is that it work for any language (including elisp literate configs) but it's a little too aggressive on it's completions.
-
copilot.el and the completion system: I'm confused
I'm trying out github copilot with this package: https://github.com/zerolfx/copilot.el, configured like this:
-
Emacs hours 2 and 3
that was enough for this to work from https://github.com/zerolfx/copilot.el
-
Helix: Release 23.03 Highlights
Devs could use the unofficial plugin for Emacs (https://github.com/zerolfx/copilot.el) as a guideline to add support
-
Parameter hints in emacs
The whole gif in the repo's README
- GitHub announces a bunch of new GPT-4 powered coding assistants. What should and could Emacs and open-source community do?
llama.cpp
-
Better and Faster Large Language Models via Multi-Token Prediction
For anyone interested in exploring this, llama.cpp has an example implementation here:
https://github.com/ggerganov/llama.cpp/tree/master/examples/...
- Llama.cpp Bfloat16 Support
-
Fine-tune your first large language model (LLM) with LoRA, llama.cpp, and KitOps in 5 easy steps
Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.
- GGML Flash Attention support merged into llama.cpp
-
Phi-3 Weights Released
well https://github.com/ggerganov/llama.cpp/issues/6849
- Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
- Llama.cpp Working on Support for Llama3
-
Embeddings are a good starting point for the AI curious app developer
Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)
Running an embedding server locally is pretty straightforward:
- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases
- Mixtral 8x22B
- Llama.cpp: Improve CPU prompt eval speed
What are some alternatives?
quelpa-use-package - Emacs quelpa handler for use-package
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
codeium.el - Free, ultrafast Copilot alternative for Emacs
gpt4all - gpt4all: run open-source LLMs anywhere
codeium.vim - Free, ultrafast Copilot alternative for Vim and Neovim
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
dotfiles - Mouseless Workflow (WIP)
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
eldoc-box - childframe doc for eglot and anything that uses eldoc
ggml - Tensor library for machine learning
chat_waitlist_signup
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM