google/hackable_diffusion ·
github.com · 557 words · saved by 1 readers
No description, website, or topics provided.
Hackable diffusion Hackable Diffusion is a modular toolbox written in Jax to experiment and educate around Diffusion modeling. Supported Integrations Gemma Fine-Tuning: Support for text diffusion models (e.g., DiffusionGemma) via a hybrid AR-diffusion implementation. The adapter package and fine-tuning configurations are located in the Gemma repository (GitHub: https://github.com/google-deepmind/gemma/tree/main/gemma/diffusion/hackable_diffusion_adapter). Philosophy The core philosophy of this library is hackability. It is designed from the ground up to be modular, composable, and easy…
saved by
related reading
- google/diffusiongemma-26B-A4B-it · Hugging Facehuggingface.co
- A Visual Guide to DiffusionGemma - by Maarten Grootendorstnewsletter.maartengrootendorst.com
- Diffusion models from scratchchenyang.co
- What are Diffusion Models?lilianweng.github.io
- Step-by-Step Diffusion: An Elementary Tutorialarxiv.org
- GitHub - google-research/tuning_playbook: A playbook for systematically maximizing the performance of deep learning models.github.com
- GitHub - jax-ml/jax: Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and moregithub.com
- Neuronpedianeuronpedia.org
- Diffusion will be everywherevarunneal.github.io
- GitHub - NVIDIA-NeMo/Automodel: 🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face supportgithub.com
- ⭐️ Diffusion Modelsandrewkchan.dev
- GitHub - CompVis/stable-diffusion: A latent text-to-image diffusion modelgithub.com