FrancescoSaverioZuppichini / Loading-huge-PyTorch-models-with-linear-memory-consumptionLinks
Little article showing how to load pytorch's models with linear memory consumption
☆34Updated 3 years ago
Alternatives and similar repositories for Loading-huge-PyTorch-models-with-linear-memory-consumption
Users that are interested in Loading-huge-PyTorch-models-with-linear-memory-consumption are comparing it to the libraries listed below
Sorting:
- An open source implementation of CLIP.☆33Updated 3 years ago
- Contains my experiments with the `big_vision` repo to train ViTs on ImageNet-1k.☆22Updated 2 years ago
- Implementation of a Transformer using ReLA (Rectified Linear Attention) from https://arxiv.org/abs/2104.07012☆49Updated 3 years ago
- Another attempt at a long-context / efficient transformer by me☆38Updated 3 years ago
- ☆75Updated 3 years ago
- FID computation in Jax/Flax.☆29Updated last year
- Implementation of "compositional attention" from MILA, a multi-head attention variant that is reframed as a two-step attention process wi…☆51Updated 3 years ago
- JAX implementation ViT-VQGAN☆82Updated 3 years ago
- A GPT, made only of MLPs, in Jax☆58Updated 4 years ago
- Re-implementation of 'Grokking: Generalization beyond overfitting on small algorithmic datasets'☆39Updated 4 years ago
- ImageNet-12k subset of ImageNet-21k (fall11)☆21Updated 2 years ago
- Implementation of the Remixer Block from the Remixer paper, in Pytorch☆36Updated 4 years ago
- Implementation of some personal helper functions for Einops, my most favorite tensor manipulation library ❤️☆57Updated 3 years ago
- Load any clip model with a standardized interface☆22Updated 2 months ago
- Minimal implementation of adaptive gradient clipping (https://arxiv.org/abs/2102.06171) in TensorFlow 2.☆86Updated 4 years ago
- Exploring an idea where one forgets about efficiency and carries out attention across each edge of the nodes (tokens)☆55Updated 9 months ago
- Cyclemoid implementation for PyTorch☆90Updated 3 years ago
- Contrastive Language-Image Pretraining☆38Updated last year
- A simple Transformer where the softmax has been replaced with normalization☆20Updated 5 years ago
- ☆27Updated 4 years ago
- Implementation of a Transformer that Ponders, using the scheme from the PonderNet paper☆81Updated 4 years ago
- Implementation of Token Shift GPT - An autoregressive model that solely relies on shifting the sequence space for mixing☆49Updated 3 years ago
- Implementation of fused cosine similarity attention in the same style as Flash Attention☆219Updated 2 years ago
- This repository hosts the code to port NumPy model weights of BiT-ResNets to TensorFlow SavedModel format.☆14Updated 4 years ago
- Experimental CUDA kernel framework unifying typed dimensions, NVRTC JIT specialization, and ML‑guided tuning.☆46Updated this week
- PyTorch reimplementation of the paper "HyperMixer: An MLP-based Green AI Alternative to Transformers" [arXiv 2022].☆18Updated 3 years ago
- Implementation of Hourglass Transformer, in Pytorch, from Google and OpenAI☆98Updated 4 years ago
- TF2 implementation of knowledge distillation using the "function matching" hypothesis from https://arxiv.org/abs/2106.05237.☆88Updated 4 years ago
- GAN models implemented with Pytorch Lightning and Hydra configuration☆33Updated 3 years ago
- Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch☆103Updated 2 years ago