gradian-ai/gradian

LoRA (Low-Rank Adaptation) inspector for Stable Diffusion

Mapping out the "memory" of neural nets with data attribution

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.

A library for mechanistic interpretability of GPT-style language models

Hypernetworks that adapt LLMs for specific benchmark tasks using only textual task description as the input

In-Context Explainability 360 toolkit