LayerNorm(SmallInit(Embedding)) in a Transformer to improve convergence
☆61Feb 21, 2022Updated 4 years ago
Alternatives and similar repositories for SmallInitEmb
Users that are interested in SmallInitEmb are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- High-performance tokenized language data-loader for Python C++ extension☆14Jul 22, 2024Updated last year
- Efficient optimizers☆314Updated this week
- ☆54Jul 16, 2025Updated 9 months ago
- ☆22Nov 9, 2024Updated last year
- ☆25Jul 30, 2025Updated 9 months 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.
- High-performance, semantic turn detection for conversational AI☆37Oct 1, 2025Updated 7 months ago
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆11Apr 22, 2026Updated last week
- PathPiece tokenizer☆14Nov 10, 2024Updated last year
- recipe for training fully-featured self supervised image jepa models☆13Jun 4, 2025Updated 10 months ago
- gzip Predicts Data-dependent Scaling Laws☆35May 28, 2024Updated last year
- ☆23Aug 26, 2023Updated 2 years ago
- Glow-TTS with Stochastic Duration Predictor and Stochastic Pitch Predictor☆19Jun 5, 2023Updated 2 years ago
- Implementation of Kronecker Attention in Pytorch☆20Sep 12, 2020Updated 5 years ago
- Implementation of LogAvgExp for Pytorch☆37Apr 10, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- This repository contains source codes for SoftCTC. Original paper can be found here: https://arxiv.org/abs/2212.02135☆19Mar 7, 2023Updated 3 years ago
- Implementation of Hyena Hierarchy in JAX☆10Apr 30, 2023Updated 3 years ago
- Speech Resynthesis and Language Modeling☆27Jun 11, 2025Updated 10 months ago
- ☆16Jun 13, 2022Updated 3 years ago
- JAX/Flax implementation of the Hyena Hierarchy☆34Apr 27, 2023Updated 3 years ago
- [ICML 24 NGSM workshop] Associative Recurrent Memory Transformer implementation and scripts for training and evaluation☆64Mar 12, 2026Updated last month
- Transformers at any scale☆42Jan 18, 2024Updated 2 years ago
- Why Do We Need Weight Decay in Modern Deep Learning? [NeurIPS 2024]☆72Sep 25, 2024Updated last year
- Course Project for COMP4471 on RWKV☆17Feb 11, 2024Updated 2 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- [ICASSP'26] Real-time streaming voice anonymization & voice conversion☆70Apr 15, 2026Updated 2 weeks ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated last year
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated 7 months ago
- Dockerfile for johnsmith0031/alpaca_lora_4bit☆12Apr 10, 2023Updated 3 years ago
- PyTorch implementation of simplified neural source filter model (s-nsf)☆14Aug 4, 2021Updated 4 years ago
- utilities for loading and running text embeddings with onnx☆45Aug 16, 2025Updated 8 months ago
- More than Just Words: Modeling Non-textual Characteristics of Podcasts☆26Nov 6, 2019Updated 6 years ago
- A minimal Pytorch Implementation of Stochastically Quantized Variational AutoEncoder (SQ-VAE) by Sony☆33Oct 16, 2023Updated 2 years ago
- Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Buil…☆51Apr 17, 2026Updated last week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆44Sep 19, 2024Updated last year
- https://x.com/BlinkDL_AI/status/1884768989743882276☆28May 4, 2025Updated 11 months ago
- Computing calibrated prediction intervals for neural network regressors☆10May 28, 2019Updated 6 years ago
- Memory-efficient transformer. Work in progress.☆19Sep 17, 2022Updated 3 years ago
- Training code for Sparse Autoencoders on Embedding models☆39Updated this week
- This repository implement a novel zero-shot TTS framework, named Flamed-TTS, focusing on the efficient generation and dynamic pacing in …☆57Aug 9, 2025Updated 8 months ago
- Code for the paper "The Impact of Positional Encoding on Length Generalization in Transformers", NeurIPS 2023☆139Apr 30, 2024Updated 2 years ago