Pinned Repositories
alfred-darkmode
An Alfred workflow to toggle Yosemite's dark and light modes.
apple-silicon-4bit-quant
Supporting code for "LLMs for your iPhone: Whole-Tensor 4 Bit Quantization"
coreml-llm-cli
CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.
CoreMLInspect
See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.
esp-lights
ESP8266-controlled WS2812s
icloud-tabs
Update iCloud tabs from Chrome.
more-ane-transformers
Run transformers (incl. LLMs) on the Apple Neural Engine.
sublime-spotify
Control Spotify from Sublime Text 2 or 3.
ue-speaker-app
App to enable Siri/Shortcuts support for UE speakers.
smpanaro's Repositories
smpanaro/coreml-llm-cli
CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.
smpanaro/more-ane-transformers
Run transformers (incl. LLMs) on the Apple Neural Engine.
smpanaro/CoreMLInspect
See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.
smpanaro/apple-silicon-4bit-quant
Supporting code for "LLMs for your iPhone: Whole-Tensor 4 Bit Quantization"
smpanaro/norm-tweaking
Post post-training-quantization (PTQ) method for improving LLMs. Unofficial implementation of https://arxiv.org/abs/2309.02784
smpanaro/mlx-squeezellm-gradients
SqueezeLLM-style gradients/Fisher Information collection in MLX
smpanaro/netron
Visualizer for neural network, deep learning, and machine learning models
smpanaro/litgpt
Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, 4-bit and 8-bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
smpanaro/QuaRot
Code for QuaRot, an end-to-end 4-bit inference of large language models.
smpanaro/swift-transformers
Swift Package to implement a transformers-like API in Swift
smpanaro/WhisperKit
Swift native on-device speech recognition with Whisper for Apple Silicon
smpanaro/whisperkittools
Python tools for WhisperKit: Model conversion, optimization and evaluation
smpanaro/AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
smpanaro/blogs.hn
tiny directory of tech blogs
smpanaro/CLIP-Finder2
CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera. Built on Apple's MobileCLIP-S0 architecture, it ensures optimal performance and accurate media retrieval.
smpanaro/coremltools
Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.
smpanaro/Elva
zstd/brotli/lz4 swift kit
smpanaro/FloatingPanel
A clean and easy-to-use floating panel UI component for iOS
smpanaro/ggml
Tensor library for machine learning
smpanaro/kmeans1d
A Python package for optimal 1D k-means clustering.
smpanaro/powerlevel10k
A Zsh theme
smpanaro/smpanaro.github.io
My personal website.
smpanaro/spotless
Keep your code spotless
smpanaro/SqueezeLLM-gradients
smpanaro/swift-chat
Mac app to demonstrate swift-transformers
smpanaro/time-series-compression
Utilities for evaluating time series compression techniques. Companion to blog post.
smpanaro/tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
smpanaro/tree-sitter-flatbuffers
tree-sitter grammar for FlatBuffers
smpanaro/zed-extensions
Extensions for the Zed editor
smpanaro/zed-flatbuffers
zed.dev extension with language support for FlatBuffers