Interactive-Active-AI/NextTransformer
Library
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 3 days ago. Wait a little before installing it.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change today.
Licence OK
MIT: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A research framework and benchmark for comparing Transformer architectures under a fixed training budget. It trains recurrent-depth, sparse and linear attention, residual-stream variants and hybrids on the same data and token count, with audited results and an observatory for…
Who it's for
ML researchers comparing Transformer architectures and efficient attention methods under equal training budgets
How to use it
Install
uv sync --frozen --extra gpu --extra upstreamFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up Interactive-Active-AI/NextTransformer in my project. Follow its README: https://github.com/Interactive-Active-AI/NextTransformer. Explain each step and check it is safe before running anything.
Star curve
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/Interactive-Active-AI/NextTransformer?ref=badge)Similar repos
- YeonwooSung/llm-architecture-from-scratch
A collection of from-scratch PyTorch implementations of modern LLM architectures, including GPT-2 XL, Llama variants, DeepSeek V3, Qwen3, and Gemma 3. A comparison table lists each model's normalizati
- aa1143/NamiGPT
A Chinese-language step-by-step tutorial that builds GPT-2 from scratch in PyTorch without using existing Transformer modules. It walks through tokenization, embeddings, attention, and blocks using a
- Prefrontal-AI/latent-sparse-attention
Research code for Latent Sparse Attention, which clusters keys hierarchically in a learned latent space so each query scores cluster centroids and attends only to selected long-range keys plus sink an
- aicodeking/PandaOrchestrator
A local LLM router that profiles a task text with a small ONNX model and picks the cheapest model likely to succeed from about 65 model cards, under a chosen mode. It returns a model name plus an esca
- OpenSenseNova/SenseNova-Loop
A 9B-parameter multimodal language model that accepts text and images and generates text, designed for long-context and agentic workflows. It uses a looped decoder block with two-stream manifold-const
- HazyResearch/ncm
Research code for Next-Concept Modeling, a two-stage framework for parallel text generation. A multiscale residual VQ tokenizer maps sequences to hierarchical discrete codes, and a transformer predict