anentropic / hft2aneLinks
Tool for exporting Apple Neural Engine-accelerated versions of transformers models on HuggingFace Hub.
☆13Updated 2 years ago
Alternatives and similar repositories for hft2ane
Users that are interested in hft2ane are comparing it to the libraries listed below
Sorting:
- CLI to demonstrate running a large language model (LLM) on Apple Neural Engine.☆116Updated 9 months ago
- See the device (CPU/GPU/ANE) and estimated cost for every layer in your CoreML model.☆23Updated last year
- ☆23Updated 2 years ago
- Run transformers (incl. LLMs) on the Apple Neural Engine.☆63Updated last year
- Tool for visual profiling Core ML models, compatible with both package and compiled versions, including reasons for unsupported operation…☆34Updated last year
- Run embedding models locally in Swift using MLTensor.☆109Updated this week
- ☆54Updated 2 years ago
- ☆41Updated 3 months ago
- A tool which checks compatibility of CoreML model with Apple Neural Engine☆13Updated 3 years ago
- Try CoreML models on multiple images and videos easily and quickly☆42Updated last year
- MLX Swift implementation of Andrej Karpathy's Let's build GPT video☆59Updated last year
- A minimalistic Swift implementation of the Jinja templating engine, specifically designed for parsing and rendering ML chat templates.☆91Updated last week
- Find out why your CoreML model isn't running on the Neural Engine!☆26Updated last year
- ☆75Updated 10 months ago
- Swift Core ML Examples☆241Updated 10 months ago
- This package provides Swift bindings for llama.cpp☆25Updated 2 years ago
- Implementation of F5-TTS in Swift using MLX☆84Updated 10 months ago
- Fork of llama.cpp, supporting Facebook's LLaMA model in Swift☆183Updated 2 years ago
- Swift for NNC☆76Updated last week
- OpenAI's Whisper ported to CoreML☆80Updated 2 years ago
- A multi-platform SwiftUI frontend for running local LLMs with Apple's MLX framework.☆422Updated 11 months ago
- mlx image models for Apple Silicon machines☆85Updated 5 months ago
- ☆189Updated 6 months ago
- Swift-based vector database for on-device RAG using MLTensor and MLX Embedders☆138Updated 2 weeks ago
- ☆120Updated 3 months ago
- MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.☆210Updated last month
- Experimenting with conversational AI in iOS, macOS and visionOS apps☆103Updated last month
- Swift package for on-device Retrieval-Augmented Generation (RAG)☆60Updated 4 months ago
- FlashAttention (Metal Port)☆538Updated last year
- Run your favourite LLMs locally on macOS from Swift☆82Updated 2 years ago