Safetensors Python Packages

fastsafetensors

High-performance safetensors model loader

netron

Visualizer for neural network, deep learning and machine learning models

hf-mem

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

mlx-model-doctor

Validate an MLX / Hugging Face model repository before you load it.

bigsmall

Lossless AI model compression - ~34% smaller with bit-identical weights; the autopilot profiles your machine, picks the highest fidelity that runs, and streams models bigger than your RAM.

pre-reasoning

LLMs take the path of least resistance. Pre-Reasoning hands any model a map of the problem first, so it unlocks the knowledge it already has, faster. For large models, that means hard problems and long-horizon tasks. For small models, consistency. Root blockers, unlock order, conflicts, parallel work. 12M params, runs locally on CPU in ~200ms.

pygpukit

Minimal GPU runtime for Python - high-performance CUDA kernels, memory management, and LLM inference without heavy dependencies

aivmlib

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

llm-harbor

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

onnx-safetensors

Use safetensors with ONNX 🤗

agent-shield-int

Agent Shield catches prompt injection attacks before they reach your LLM.

sft-cli

An interactive terminal browser for `.safetensors` files

diffai-python

Python bindings for diffai, an AI/ML model diff tool comparing PyTorch, Safetensors, NumPy and MATLAB tensors

kn-dataset-tools

An Extensive AI & Camera Metadata Viewer

bampe-weights

This repository is for profiling, extracting, visualizing and reusing generative AI weights to hopefully build more accurate AI models and audit/scan weights at rest to identify knowledge domains for risk(s).

needle-rs

258 KB WASM runtime for Needle a 26M-parameter tool-calling transformer. Runs in browser, Cloudflare Workers, and Node.js. No backend required.

modelsig

Compare LLM architectures without downloading weights — structural fingerprint & proxy-test advisor for vLLM, TensorRT-LLM, SGLang, ONNX Runtime

mlx-triage

MLX Inference Quality Diagnostic Toolkit

safetensors-streaming

Stream safetensors files from HTTP/S3 directly to GPU memory

tensorshare

🤝 Trade any tensors over the network

safe-view

A terminal application to view safetensors files

agent-strike

Agent Strike — Offensive LLM Security Testing. Coming soon by Sandeep.

safejax

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

adaptersentry

Static security scanner for LoRA adapters — detects anomalous weight patterns in .safetensors files