big-AGI
llama.cpp
big-AGI | llama.cpp | |
---|---|---|
8 | 780 | |
4,445 | 58,425 | |
- | - | |
10.0 | 10.0 | |
3 days ago | 3 days ago | |
TypeScript | 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.
big-AGI
- GPT-4 Turbo with Vision is a step backwards for coding
- LM Studio – Discover, download, and run local LLMs
- ChatGPT Voice Announced (By Greg Brockman)
-
Is there an easy way to use the March 14th model ChatGPT-4 model?
You could run a local copy of big-agi and edit this file to use the dated model.
-
Managing ChatGPT token/character limits tool
As ChatGPT counts tokens for both inputs and output, you'd have to be thoughtful for the input side as well so this is where the tool would come in handy within the same chat session. I don't think it remembers separate chat sessions so yeah without access to history, you'd need to either start a new chat session each time or setup your own ChatGPT instance and use your own OpenAI API token and be billed. For my own ChatGPT instance I use awesome app at https://github.com/enricoros/nextjs-chatgpt-app which has a demo on the readme page too.
-
Make your own ChatGPT UI
nice, maybe you can make the initializing prompts in
https://github.com/enricoros/nextjs-chatgpt-app/blob/main/pa...
transparent to the user and even changeable by them.
llama.cpp
-
IBM Granite: A Family of Open Foundation Models for Code Intelligence
if you can compile stuff, then looking at llama.cpp (what ollama uses) is also interesting: https://github.com/ggerganov/llama.cpp
the server is here: https://github.com/ggerganov/llama.cpp/tree/master/examples/...
And you can search for any GGUF on huggingface
-
Ask HN: Affordable hardware for running local large language models?
Yes, Metal seems to allow a maximum of 1/2 of the RAM for one process, and 3/4 of the RAM allocated to the GPU overall. There’s a kernel hack to fix it, but that comes with the usual system integrity caveats. https://github.com/ggerganov/llama.cpp/discussions/2182
- Xmake: A modern C/C++ build tool
-
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
What are some alternatives?
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
Lobe Chat - LobeChat is a open-source, extensible (Function Calling), high-performance chatbot framework.It supports one-click free deployment of your private ChatGPT/LLM web application.
gpt4all - gpt4all: run open-source LLMs anywhere
chatgpt-demo - Minimal web UI for ChatGPT.
fill - Generative fill in 3D.
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
chatbot-ui - AI chat for every model.
ggml - Tensor library for machine learning
ollama-webui - ChatGPT-Style WebUI for LLMs (Formerly Ollama WebUI) [Moved to: https://github.com/open-webui/open-webui]
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM