Top 3 Python Coremltool Projects

CoreML-Models

2 6,212 2.3 Python

Largest list of models for Core ML (for iOS 11+)
coremltools

11 4,037 8.7 Python

Core ML tools contain supporting tools for Core ML model conversion, editing, and validation.

Project mention: CoreML commit from Apple mentions iOS17 exclusive features | /r/u_Standard-Sundae-6011 | 2023-06-03

InfluxDB

www.influxdata.com sponsored

Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
exporters

3 525 7.1 Python

Export Hugging Face models to Core ML and TensorFlow Lite

Project mention: I made an app that runs Mistral 7B 0.2 LLM locally on iPhone Pros | news.ycombinator.com | 2024-01-07

Conceptually, to the best of my understanding, nothing too serious; perhaps the inefficiency of processing a larger input than necessary?
Practically, a few things:
If you want to have your cake & eat it too, they recommend Enumerated Shapes[1] in their coremltools docs, where CoreML precompiles up to 128 (!) variants of input shapes, but again this is fairly limiting (1 tok, 2 tok, 3 tok... up to 128 token prompts.. maybe you enforce a minimum, say 80 tokens to account for a system prompt, so up to 200 tokens, but... still pretty short). But this is only compatible with CPU inference, so that reduces its appeal.
It seems like its current state was designed for text embedding models, where you normalize input length by chunking (often 128 or 256 tokens) and operate on the chunks — and indeed, that’s the only text-based CoreML model that Apple ships today, a Bert embedding model tuned for Q&A[2], not an LLM.
You could used a fixed input length that’s fairly large; I haven’t experimented with it once I grasped the memory requirements, but from what I gather from HuggingFace’s announcement blog post[3], it seems that is what they do with swift-transformers & their CoreML conversions, handling the details for you[4][5]. I haven’t carefully investigated the implementation, but I’m curious to learn more!
You can be sure that no one is more aware of all this than Apple — they published "Deploying Transformers on the Apple Neural Engine" in June 2022[6]. I look forward to seeing what they cook up for developers at WWDC this year!
---
[1] "Use `EnumeratedShapes` for best performance. During compilation the model can be optimized on the device for the finite set of input shapes. You can provide up to 128 different shapes." https://apple.github.io/coremltools/docs-guides/source/flexi...
[2] BertSQUAD.mlmodel (fp16) https://developer.apple.com/machine-learning/models/#text
[3] https://huggingface.co/blog/swift-coreml-llm#optimization
[4] `use_fixed_shapes` "Retrieve the max sequence length from the model configuration, or use a hardcoded value (currently 128). This can be subclassed to support custom lengths." https://github.com/huggingface/exporters/pull/37/files#diff-...
[5] `use_flexible_shapes` "When True, inputs are allowed to use sequence lengths of `1` up to `maxSequenceLength`. Unfortunately, this currently prevents the model from running on GPU or the Neural Engine. We default to `False`, but this can be overridden in custom configurations." https://github.com/huggingface/exporters/pull/37/files#diff-...
[6] https://machinelearning.apple.com/research/neural-engine-tra...

NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020). The latest post mention was on 2024-01-07.