Visualizer for neural network, deep learning and machine learning models

One command brings a complete pre-wired LLM stack with hundreds of services to explore.

A CLI to estimate inference memory requirements for Hugging Face models, written in Python.

Convert your Stable Diffusion checkpoints quickly and easily.

Powerful Powerful Machine Learning library with GPU, CPU and WASM backends

AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure your AI supply chain today! ⚙️🛡️

Stable Diffusion UI: Diffusers (CUDA/ONNX)

High-performance safetensors model loader

Utility for Safetensors Files

Executable Stable Diffusion merge recipes in comfyui

Gradio based tool to run opensource LLM models directly from Huggingface

Use safetensors with ONNX 🤗

A Simple Viewer for EXIF and AI Metadata

A utility to inspect, validate, sign and verify machine learning model files.

ComfyUI custom nodes for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis

A lightweight tool to locally manage, back up, and organize SafeTensors model metadata from Civitai.

Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`

Python script that converts PyTorch pth and pt files to safetensors format

Easily train and inference on your personal computer, no need for large scale clusters!

Modern Stable Diffusion models family - Fluently

🤝 Trade any tensors over the network

SwiftLet is a lightweight Python framework for running open-source Large Language Models (LLMs) locally using safetensors

ForgeUI/WebUI extension to find trained keywords for a LoRA models.

Aivis Voice Model File (.aivm/.aivmx) Utility Library

High-performance Python librarys for connecting AI/ML frameworks with OSS storage.

Safetensors dump and load in Elixir

Aivis Voice Model File (.aivm/.aivmx) Generator / Editor

Swift package for reading and writing Safetensors files.

EHRM [ Electronic Health Record Management ] introduces a centralized platform for analyzing patient records, offering insights into billing amounts, demographics, prevalent diagnoses, medical conditions, consulted doctors, admission types, and medication usage.

This project demonstrates the process of fine-tuning the Qwen2.5-3B-Instruct model using GRPO (Generalized Reward Policy Optimization) on the GSM8K dataset.