A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Local AI, native to your Mac. Chat, serve, monitor, and connect MLX models from one macOS app.

A modular Swift SDK for audio processing with MLX on Apple Silicon

MLX-Embeddings is the best package for running Vision and Language Embedding models locally on your Mac using MLX.

MLX-Video is the best package for inference and finetuning of Image-Video-Audio generation models on your Mac using MLX.

Here is a tutorial on how to implement a research Paper with Keras

Deploy and scale Large Language Models (LLMs) in production.

No repository description provided.

FastMLX is a high performance production ready API to host MLX models.

Run LLMs with MLX

No repository description provided.

Reachy Mini's SDK

This repository is a curated collection of resources, tutorials, and practical examples designed to guide you through the journey of mastering CUDA programming. Whether you're just starting or looking to optimize and scale your GPU-accelerated applications.

Talk with Reachy Mini!

Data science, AI and Machine Learning

No repository description provided.

MLX: An array framework for Apple silicon

A Swift client for Hugging Face Hub and Inference Providers APIs

Inworld TTS

This where I put my crazy projects that I do when I'm bored or inspired by the boredom

A framework for efficient model inference with omni-modality models

Frontier Open-Source Voice AI

model activation visualiser

gsm8k eval in MLX.

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models

🦜🔗 Build context-aware reasoning applications

Grok open release

No repository description provided.

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

LLMs and VLMs with MLX Swift

Examples in the MLX framework

"LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", Accepted to ACL 2024

Claude Engineer is an interactive command-line interface (CLI) that leverages the power of Anthropic's Claude-3.5-Sonnet model to assist with software development tasks. This tool combines the capabilities of a large language model with practical file system operations and web search functionality.

A framework for few-shot evaluation of language models.

Gemma 2B with 10M context length using Infini-attention.

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

PyTorch implementation of Infini-Transformer from "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" (https://arxiv.org/abs/2404.07143)

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".

Notes on the Mistral AI model

Minimalist ML framework for Rust

No repository description provided.

Semantic Segmentation Suite in TensorFlow. Implement, train, and test new Semantic Segmentation models easily!

jPlayer : HTML5 Audio & Video for jQuery

No repository description provided.

A fork to add multimodal model training to open-r1

Examples using MLX Swift

Clean, accessible reproduction of DeepSeek R1-Zero

[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

Fast and accurate automatic speech recognition (ASR) for edge devices

No repository description provided.

The official repo of Qwen2-Audio chat & pretrained large audio language model proposed by Alibaba Cloud.

Go ahead and axolotl questions

This is our own implementation of 'Layer Selective Rank Reduction'

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation applied to llama 3 8b

Toolkit is a collection of prebuilt components enabling users to quickly build and deploy RAG applications.

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

No repository description provided.

No repository description provided.

No repository description provided.

No repository description provided.

No repository description provided.

Approximation of the Claude 3 tokenizer by inspecting generation stream

No repository description provided.

ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases

No repository description provided.

JS Client library for Mistral AI platform

Ship RAG based LLM web apps in seconds.

No repository description provided.

Data platform for LLMs - Load, index, retrieve and sync any unstructured data

fine tuning mistral 7B using Huggingface, Weights and Biases, Choline, and Vast AI

No repository description provided.

Library for Textless Spoken Language Processing

Chat language model that can interpret and execute functions/plugins

No repository description provided.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

notes for Machine Learning -- Applications course

This is a repository for an introductory course in Machine Learning carried out at Wroclaw University of Science and Technology for Big Data Analytics.

No repository description provided.

code for the ddp tutorial

Build and train PyTorch models and connect them to the ML lifecycle using Lightning App templates, without handling DIY infrastructure, cost management, scaling, and other headaches.

Kaggle Python docker image

An end-to-end implementation of intent prediction with Metaflow and other cool tools

Sacred is a tool to help you configure, organize, log and reproduce experiments developed at IDSIA.

Codebase for the blog post "24 Evaluation Metrics for Binary Classification (And When to Use Them)"

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

scikit-learn: machine learning in Python

No repository description provided.

No repository description provided.

No repository description provided.

No repository description provided.

No repository description provided.

No repository description provided.

Notebooks for the "A walk with fastai2" Study Group and Lecture Series

Draft of the fastai book

Curated lists of fastai resources: blog posts, twitter threads etc.

No repository description provided.

Minimal setup for building a Python API running with Flask and MongoDB, inside Docker Containers