SimplifiedTransformer simplifies transformer block without affecting training. Skip connections, projection parameters, sequential sub-blocks, and normalization layers are removed. Experimental results confirm similar training speed and performance.
☆16Oct 2, 2026Updated last week
Alternatives and similar repositories for SimplifiedTransformers
Users that are interested in SimplifiedTransformers 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 suite of finetuned LLMs for atomically precise function calling 🧪☆16Updated this week
- Implementation of a Hierarchical Mamba as described in the paper: "Hierarchical State Space Models for Continuous Sequence-to-Sequence Mo…☆16Nov 11, 2024Updated last year
- Implementation of the model "Hedgehog" from the paper: "The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry"☆15Mar 11, 2024Updated 2 years ago
- Multi-threading, Concurrency, Asynchrony, and various Execution Methods implemented in a Rust backend for bleeding edge performance.☆23Nov 11, 2024Updated last year
- Pytorch Implementation of Deepmind's SIMA: "Scaling Instructable Agents Across Many Simulated Worlds"☆36Jun 17, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A chinese singing voice dataset, professional male singer, 105 songs, 132 minutes☆13Oct 19, 2023Updated 2 years ago
- The source code for the paper CrossSinger (asru2023)☆18Oct 12, 2023Updated 3 years ago
- This is the accompanying repository to the paper - Automatic Estimation of Singing Voice Musical Dynamics☆16Oct 28, 2024Updated last year
- SinGlow is a part of my Singing voice synthesis system. It can extract features of sound, particularly songs and musics. Then we can use …☆11Oct 9, 2021Updated 5 years ago
- The open source implementation of the cross attention mechanism from the paper: "JOINTLY TRAINING LARGE AUTOREGRESSIVE MULTIMODAL MODELS"☆37Mar 11, 2024Updated 2 years ago
- Deploy your autonomous agents to production grade environments with 99% Uptime Guarantee, Infinite Scalability, and self-healing.☆58Aug 12, 2026Updated 2 months ago
- ☆15Apr 16, 2026Updated 5 months ago
- ☆17Mar 31, 2025Updated last year
- ☆19Feb 2, 2023Updated 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.
- Vocal Remover using Deep Neural Networks☆21Dec 31, 2024Updated last year
- Bilingual Singing Voice Synthesis☆18Mar 25, 2024Updated 2 years ago
- [ICMR 2025] Official Repository for The Paper, Let Network Decide What to Learn: Symbolic Music Understanding Model Based on Large-scale …☆19Aug 17, 2025Updated last year
- Implementation of Qformer from BLIP2 in Zeta Lego blocks.☆51Nov 11, 2024Updated last year
- An AR+AR TTS attempt.☆18Jan 13, 2025Updated last year
- Mutiband version of HIFIGAN☆19Nov 6, 2020Updated 5 years ago
- Public female English corpus used for Project AI❤dol☆16Dec 28, 2025Updated 9 months ago
- [ICME 2024 oral] Official Repository for The Paper, PianoBART: Symbolic Piano Music Understanding and Generating with Large-Scale Pre-Tra…☆23Aug 17, 2025Updated last year
- Just another FastSpeech 2 but cleaner code :)☆29Jun 28, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Singing Voice Synthesis System based on Sinsy☆23Mar 3, 2020Updated 6 years ago
- The implementation of Paper: Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement.☆21Aug 1, 2026Updated 2 months ago
- On-device real-time RAG App built using Jina Reader, Mediapipe, Gemma 2b IT LLM.☆15Apr 15, 2024Updated 2 years ago
- ☆16Dec 11, 2023Updated 2 years ago
- Some Thoughts on AI Alignment: Using AI to Control AI☆16Feb 25, 2025Updated last year
- Answer questions against collections stored in LLM using Retrieval Augmented Generation☆30Jan 29, 2024Updated 2 years ago
- Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark☆38May 7, 2025Updated last year
- Multiplayer UNO card game with real-time gameplay, voice chat, and house rule☆27Sep 20, 2026Updated 3 weeks ago
- Music generation☆25May 2, 2024Updated 2 years ago
- 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.
- ☆18Dec 18, 2023Updated 2 years ago
- Community Implementation of the paper: "Multi-Head Mixture-of-Experts" In PyTorch☆31Oct 2, 2026Updated last week
- A swarm of LLM agents that will help you test, document, and productionize your code!☆20Updated this week
- ☆18Dec 18, 2023Updated 2 years ago
- This was my final year project. I used MATLAB with multiple libraries to achieve successful porotype software. The prototype implemented …☆10Dec 5, 2016Updated 9 years ago
- Modified Score-Entropy-Discrete-Diffusion to do a character level ml model and integrate with Oxen☆22Apr 26, 2024Updated 2 years ago
- [NeurIPS 2024] Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution☆38Dec 23, 2024Updated last year