coremltools
docker
coremltools | docker | |
---|---|---|
11 | 152 | |
4,063 | 516 | |
1.3% | 1.0% | |
8.7 | 0.0 | |
11 days ago | 3 days ago | |
Python | Go | |
BSD 3-clause "New" or "Revised" License | Apache License 2.0 |
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.
coremltools
- CoreML commit from Apple mentions iOS17 exclusive features
-
Lisa Su Saved AMD. Now She Wants Nvidia's AI Crown
Instead of trying to integrate the whole stack of, say, pytorch, Apple's primary approach has been converting models to work with Apple's stack.
https://github.com/apple/coremltools
Clearly no one is going to be doing training or even fine tuning on Apple hardware at any scale (it competes at the low end, but at scale you invariably will be using nvidia hardware), but once you have a decent model it's a robust way of using it on Apple devices.
-
Stable Diffusion for M1 iPad
There is one guy who was able to run it on iOS. See this thread for more information. Basically, the idea is to convert torch models to CoreMl. Only the CLIP tokenizer's implementation is currently missing. I guess this guy will keep modifications private, but he is trying to optimize model for lower RAM requirements.
-
MacBook Pro 14” M1 Pro (worth buying for programming)
Afaik (correct me if I’m wrong) both PyTorch and tensorflow only use the gpu when training and not the neural engine. I think the neural engines can be used for inference if the model is in the CoreML format (https://github.com/apple/coremltools)
- Is it possible to convert a yolov5 model to a CoreML/.mlmodel to work in an IOS app?
-
ML model conversion
CoreML Tools
-
Supreme Court, in a 6–2 ruling in Google v. Oracle, concludes that Google’s use of Java API was a fair use of that material
And Python.
-
Apple’s New M1 Chip is a Machine Learning Beast
There's literally an Apple provided tool, called [coremltools[(https://github.com/apple/coremltools) to convert many common PyTorch and TensorFlow models to CoreML.
docker
- Live reload em Go com docker e compile daemon
-
My Favorite DevTools to Build AI/ML Applications!
Deploying AI models into production requires tools that can package applications and manage them at scale. Docker simplifies the deployment of AI applications by containerizing them, ensuring that the application runs smoothly in any environment. Kubernetes, an orchestration system for Docker containers, allows for the automated deployment, scaling, and management of containerized applications, essential for AI applications that need to scale across multiple servers or cloud environments.
-
Ask HN: What software sparks joy when using?
Linux Mint with Cinnamon: https://www.linuxmint.com/ as far as desktop OSes go it's familiar (Ubuntu without snaps by default), whereas the UI feels both snappy, doesn't use too much resources and is actually pretty to look at.
MobaXTerm: https://mobaxterm.mobatek.net/ this one is a bit more Windows centric but I ended up paying for it and replaced mRemoteNg and PuTTY with it, it's even better than Remmina or whatever Linux has to offer - you can manage SSH/RDP/VNC/... sessions, input across multiple sessions side by side and it just simplifies things a lot (jump host support, a port forwarding too and so much more).
GitKraken: https://www.gitkraken.com/ also a piece of software that I paid for, this one actually makes using Git pleasant, feels better to use than SourceTree and Git Cola (even though that latter is wonderfully lightweight, too) and honestly I prefer that to the CLI nowadays.
Kanboard: https://kanboard.org/ is a lightweight Kanban project management tool, it might not have every feature under the sun but it's the most snappy project management tool I've ever used, looks simple and runs well. I honestly love it, what a nice thing to have.
Most modern text editors and IDEs: I personally pay for JetBrains IDEs but also like Visual Studio Code as a text editor and both have helped me immensely, they're reasonably performant when you have the RAM, look nice, often give you suggestions about how to improve your code and also have a plethora of plugins in their ecosystems. Nowadays I unapologetically use LLMs as well and overall it feels like I have these great tools and cool autocomplete (that is sometimes a bit silly and wrong) at my disposal, that makes me happy.
Kdenlive: https://kdenlive.org/ imagine if there was a successor to Windows Movie Maker, though something that gets most of the important stuff out of Sony Vegas, except is also completely free and works on most platforms. Kdenlive is all of that and also somehow quite pleasant to use, I actually prefer it to DaVinci resolve. There is a bit of a learning curve to any piece of software like this, but everything mostly makes sense in this one.
Gitea: https://about.gitea.com/ I still use this for my personal Git repositories and integrating with CI systems and it's lightweight, looks good and just feels pleasant to use. Previously I self-hosted GitLab and constantly ran into resource exhaustion as well as doubts about the next update is going to corrupt all of my data and break (it did), so now I use Gitea instead.
Drone CI: https://www.drone.io/ a container native CI solution that I can also self host. It's container oriented, integrates with Gitea nicely, is similarly nice to GitLab CI and doesn't cause me headaches like Jenkins would.
Docker: https://www.docker.com/ yes, even Docker desktop. It just makes working with containers really pleasant and predictable, even when something like Podman also exists (and also is great). I don't know, I feel like Docker really saved me from having brittle legacy environments, even self-contained containers with health checks and resource limits with still the same brittle code inside of those make me feel way more safe.
-
Build and deploy a REST API with Postgres database in TypeScript
Note: Before running your application in the next step, make sure you have Docker installed and running. It's required to locally run Encore applications with databases.
-
Introducing WP Setup
Developing WordPress plugins and themes often requires a reliable development environment. Current we have good solutions as wp-env from Autommatic, Local WP from WP Engine, Docker, XAMPP (for old ones) and so on. All this can be good suits for a development environment, specially Local WP that is probably the easiest one to get up and running and wp-env that leverages Docker as a development environment in a very easy way to use.
-
Building Scalable GraphQL Microservices With Node.js and Docker: A Comprehensive Guide
Docker, an open-source development platform, provides containerization technology for building and packaging applications along with their dependencies into portable images.
-
Building Llama as a Service (LaaS)
With each app containerized with Docker, this allows it to be run on any other developer's machine also running Docker. Although I had automated deployments to Heroku without this, I decided to upload each service to a container registry.
-
Exploring 7 Efficient Alternatives to MAMP for Local Development Environments
Docker
-
The power of the CLI with Golang and Cobra CLI
Today we are going to see all the power that a CLI (Command line interface) can bring to development, a CLI can help us perform tasks more effectively and lightly through commands via terminal, without needing an interface. For example, git and Docker, we practically use their CLI all the time, when we execute a git commit -m "commit message" or docker ps -a we are using a CLI. I'm going to leave an article that details what a CLI is.
-
Simplest Guide to DIY Your Own LLM Toy in 2024
Docker (required): Understanding Docker is crucial for deploying software in containers, making your project portable and scalable. I use it for start Folo server.
What are some alternatives?
RobustVideoMatting - Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
SillyTavern - LLM Frontend for Power Users.
Pytorch - Tensors and Dynamic neural networks in Python with strong GPU acceleration
SillyTavern-extras - Extensions API for SillyTavern [Moved to: https://github.com/SillyTavern/SillyTavern-extras]
tensorflow_macos - TensorFlow for macOS 11.0+ accelerated using Apple's ML Compute framework.
SillyTavern-Extras - Extensions API for SillyTavern.
3d-model-convert-to-gltf - Convert 3d model (STL/IGES/STEP/OBJ/FBX) to gltf and compression
winget-pkgs - The Microsoft community Windows Package Manager manifest repository
MMdnn - MMdnn is a set of tools to help users inter-operate among different deep learning frameworks. E.g. model conversion and visualization. Convert models between Caffe, Keras, MXNet, Tensorflow, CNTK, PyTorch Onnx and CoreML.
SillyTavern - LLM Frontend for Power Users. [Moved to: https://github.com/SillyTavern/SillyTavern]
password-manager-resources - A place for creators and users of password managers to collaborate on resources to make password management better.
hummingbird - Hummingbird compiles trained ML models into tensor computation for faster inference.