Popular GitHub Repositories for M365

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

TinyML AI inference library

Word GPT Plus is a word add-in which integrates the chatGPT model into Microsoft Word. Both official and web api is supported.

Auto-Update your M3U Playlists every day without needing an app, with the same link.

Large-Scale Visual Representation Model

Object detection on multiple datasets with an automatically learned unified label space.

An all-in-one AI audio playground using Cloudflare AI Workers to transcribe, analyze, summarize, and translate any audio file.

Providing reproducibility in deep learning frameworks

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.

将EPUB、PDF和文本文件转换成带同步字幕的有声书。

? Kokoro Web: Free AI text-to-speech, online or self-hosted, OpenAI compatible!

VoxNovel: generate audiobooks giving each character a different voice actor.

TensorFlow Metal Backend on Apple Silicon Experiments (just for fun)

The TensorFlow reference implementation of 'GEMSEC: Graph Embedding with Self Clustering' (ASONAM 2019).

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification

A few quick scripts focused on testing TensorFlow/PyTorch/Llama 2 on macOS.

Code for paper "Discourse-Aware Neural Extractive Text Summarization" (ACL20)

An implementation of "Community Preserving Network Embedding" (AAAI 2017)

Half Wavelet Attention on M-Net+ for Low-light Image Enhancement