predictive-spy
ml-ferret | predictive-spy | |
---|---|---|
3 | 7 | |
7,911 | 121 | |
4.2% | - | |
4.3 | 4.7 | |
4 months ago | 4 months ago | |
Python | Python | |
GNU General Public License v3.0 or later | 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.
ml-ferret
predictive-spy
-
Ferret: An End-to-End MLLM by Apple
According to this article[1] it has about 34 million parameters.
https://jackcook.com/2023/09/08/predictive-text.html
- A look at Apple’s new Transformer-powered predictive text model
- Apple UniLM: new 34M-parameter language model built into upcoming iOS
-
[P] A look at Apple’s new Transformer-powered predictive text model
- GitHub: https://github.com/jackcook/predictive-spy
What are some alternatives?
FLaNK-VectorDB - NiFi and Vector Databases
EfficientFormer - EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]
llm-classifier - Classify data instantly using an LLM
function-identification - This project demonstrates how a convolutional neural network can be used to detect the boundaries of a function in compiled code
mlx - MLX: An array framework for Apple silicon
kgpt - A custom GPT based on [Zero To Hero](https://karpathy.ai/zero-to-hero.html) utilizing tiktoken with the intent to augment AI Transformer-model education and reverse engineer GPT models from scratch.
pong-wars
CoreML-Models - Largest list of models for Core ML (for iOS 11+)
gateway - A Blazing Fast AI Gateway. Route to 100+ LLMs with 1 fast & friendly API.
AppleNeuralHash2ONNX - Convert Apple NeuralHash model for CSAM Detection to ONNX.
InstantID - InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥
get-the-news-rss-atom-feed-summary - Get a summary of the most recent news from an RSS or Atom feed using Amazon Bedrock.