Compression schema for gradients of activations in backward pass
☆45Jul 26, 2023Updated 3 years ago
Alternatives and similar repositories for fewbit
Users that are interested in fewbit are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A neural network training framework within a task-based parallel programming paradigm☆55Updated this week
- Quadrature-based features for kernel approximation☆16Oct 30, 2018Updated 7 years ago
- ☆11Dec 6, 2020Updated 5 years ago
- Faster and Lighter LoRA Implementations☆13Nov 21, 2024Updated last year
- Gradient-free optimization method for the multidimensional arrays and discretized multivariate functions based on the tensor train (TT) f…☆41Apr 29, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Python bindings to llama.cpp☆27Mar 22, 2023Updated 3 years ago
- Global Weather Forecasting from Mid-Range to Subseasonal Scale☆19Mar 26, 2026Updated 4 months ago
- Python progress bar with rich output that uses native ipython functionality. Widget-free. Works even in JupyterLab.☆39Feb 10, 2019Updated 7 years ago
- MUSCO: MUlti-Stage COmpression of neural networks☆72Feb 16, 2021Updated 5 years ago
- Metamodeling, sensitivity analysis and visualization using the tensor train format☆21Sep 8, 2022Updated 3 years ago
- Gradient-free optimization method for multivariable functions based on the low rank tensor train (TT) format and maximal-volume principle…☆39Jul 27, 2023Updated 3 years ago
- Telegram notification with IPython magics.☆61Jul 10, 2023Updated 3 years ago
- Deep learning @ Skoltech @ 2023☆64May 14, 2023Updated 3 years ago
- Code for "Exponential Family Estimation via Adversarial Dynamics Embedding" (NeurIPS 2019)☆14Nov 26, 2019Updated 6 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561☆25Mar 30, 2021Updated 5 years ago
- ☆16Dec 9, 2023Updated 2 years ago
- Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent☆16Sep 8, 2022Updated 3 years ago
- ☆11Feb 2, 2024Updated 2 years ago
- ☆26Nov 8, 2021Updated 4 years ago
- ☆15Apr 26, 2022Updated 4 years ago
- (AAAI 2026) First-Order Error Matters: Accurate Compensation for Quantized Large Language Models☆17Apr 16, 2026Updated 3 months ago
- Fork of Flame repo for training of some new stuff in development☆20Updated this week
- BESA is a differentiable weight pruning technique for large language models.☆17Mar 4, 2024Updated 2 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- This is th code to FAT method with links to quantized tflite models. (CC BY-NC-ND)☆19Dec 20, 2018Updated 7 years ago
- Code for MSID, a Multi-Scale Intrinsic Distance for comparing generative models, studying neural networks, and more!☆52May 29, 2019Updated 7 years ago
- NMF/NTF with Pytorch☆17Mar 24, 2019Updated 7 years ago
- Evolutionary generation of efficient GPU kernels☆33Jul 8, 2026Updated last month
- Python based GBDT implementation☆30Feb 9, 2022Updated 4 years ago
- Catalyst.RL: A Distributed Framework for Reproducible RL Research☆38Mar 17, 2019Updated 7 years ago
- Fortran non-linear system of equations solver with documentation☆19Jun 30, 2020Updated 6 years ago
- ☆10Aug 5, 2020Updated 6 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆20Oct 9, 2022Updated 3 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity (ACL 2025, oral)☆35Jun 14, 2025Updated last year
- A collection of optimizers, some arcane others well known, for Flax.☆29Aug 6, 2021Updated 5 years ago
- Code for reproducing the results from "CrAM: A Compression-Aware Minimizer" accepted at ICLR 2023☆10Mar 1, 2023Updated 3 years ago
- ☆15Sep 14, 2021Updated 4 years ago
- A framework based on the tensor train decomposition for working with multivariate functions and multidimensional arrays☆69Nov 20, 2025Updated 8 months ago
- ☆11Feb 5, 2026Updated 6 months ago
- ☆12Mar 16, 2022Updated 4 years ago