local.ai
llama.cpp
local.ai | llama.cpp | |
---|---|---|
4 | 782 | |
535 | 58,425 | |
- | - | |
8.7 | 10.0 | |
8 months ago | 4 days ago | |
TypeScript | C++ | |
GNU General Public License v3.0 only | 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.
local.ai
-
Why does GPT4all respond so slowly on my machine?
I tried to launch gpt4all on my laptop with 16gb ram and Ryzen 7 4700u. Gpt4all doesn't work properly. It uses igpu at 100% level instead of using cpu. And it can't manage to load any model, i can't type any question in it's window. Faraday.dev, secondbrain.sh, localai.app, lmstudio.ai, rwkv runner, LoLLMs WebUI, kobold cpp: all these apps run normally. Only gpt4all and oobabooga fail to run.
-
All AI Models, from 3B to 13B running at ~0.5 tokens/s, what could be causing this?
Sidenote: can you try out localai.app and see if it's faster than oobabooga on your end? (It's all CPU inferencing as well, but just curious if there's any speed gain).
-
Releasing local.ai - an LLM local playground with minimal setup
Thank you. When I first started the project and got the domain localai.app, I had no idea LocalAI was a thing. A friend of mine forwarded me a link to that project mid May, and I was like dang it, let's just add a dot and call it a day (for now...) - local "dot" ai vs LocalAI lol
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?
LocalAI - :robot: The free, Open Source OpenAI alternative. Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. It allows to generate Text, Audio, Video, Images. Also with voice cloning capabilities.
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
chatgpt-api-example - Batman/Alfred chatbot example with ChatGPT API
gpt4all - gpt4all: run open-source LLMs anywhere
pnpm - Fast, disk space efficient package manager
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
qadog - QA agent that follows user stories
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
window.ai - Use your own AI models on the web
ggml - Tensor library for machine learning
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM
FastChat - An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.