# Interactive-Active-AI/NextTransformer

> An open framework and benchmark for comparing Transformer architectures (recurrent depth, linear and sparse attention, hybrids) under a fixed training budget, plus a platform for autonomous architecture research by agents.

- Magnitude: 4.9 out of 10 — Early signal
- Stars: 154 total · +8 stars measured 2026-11-02, 08:35–10:52 UTC, ≈ 47 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-10-31 · Last push: 2026-11-02
- GitHub: https://github.com/Interactive-Active-AI/NextTransformer · Homepage: https://interactive-active-ai.github.io/NextTransformer/ · Page: https://gitnova.dev/en/r/Interactive-Active-AI/NextTransformer

## Useful for

- Train a custom attention architecture under the shared protocol and compare it with the baseline on the leaderboard
- Add a method as a plugin and calibrate it to the shared FLOPs budget
- Run multi-node training on 2 nodes x 8 GPUs via accelerate or Slurm

## Why it’s here

- Star-counter measurements on 2026-11-02 (UTC), 08:35–10:52: 146 → 154 stars (+8). This is the change over that interval.
- Estimated end-of-day forecast: about +47 stars, using observed gains and the previous day.
- The repository is 2 days old and already has 154 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #164.
- About 5 forks a day — people are taking the code.

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 8
- Issues and pull requests: 8
- Watchers: 4
- Average over the last week: 64 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 1

## Stars per day, last 3 days (oldest → newest, today is partial)

2026-10-31 … 2026-11-02: 23, 121, 8

## Spotted in now

- Top new repositories this week: #164

## More in this category

1. **togg53192-cmd/jailbreaks** — 6.3 · Peaking · Language models · +447 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 936 by evening
   A collection of 31 system prompts, persona locks, and AGENTS.md files for 25+ models (Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Gemma, GPT-OSS). Intended for research on how instruction hierarchies and policy overrides affect model…
   Full card: https://gitnova.dev/en/r/togg53192-cmd/jailbreaks.md
2. **FlashML-org/FreeToken** — 5.9 · Breakout · Language models · Python · +327 stars measured 2026-11-02, 00:07–10:52 UTC, ≈ 674 by evening
   A Mixture-of-Experts inference engine for running frontier-scale open-weight MoE models (290B+) on consumer hardware — GPUs, CPUs, and host memory. Aimed at users who want to run frontier models locally.
   Full card: https://gitnova.dev/en/r/FlashML-org/FreeToken.md
3. **JustVugg/colibri** — 5.2 · Breakout · Language models · C · +303 stars measured 2026-11-02, 00:08–10:52 UTC, ≈ 635 by evening
   A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.
   Full card: https://gitnova.dev/en/r/JustVugg/colibri.md
4. **p-e-w/heretic** — 4.8 · Breakout · Language models · Python · +176 stars measured 2026-11-02, 00:09–10:52 UTC, ≈ 378 by evening
   A tool for fully automatic removal of censorship (safety alignment) from transformer-based language models using directional ablation and Optuna-based parameter optimization.
   Full card: https://gitnova.dev/en/r/p-e-w/heretic.md
5. **Niko1221/Strata** — 4.5 · Steady · Language models · C++ · +369 stars measured 2026-11-02, 00:08–10:52 UTC, ≈ 784 by evening
   A C++ local inference engine that runs the 125B MoE model Qwen3.8-Flash-Next on a regular PC with one NVIDIA GPU (12-24 GB) and 64 GB RAM, exposing an OpenAI/Anthropic-compatible API on localhost.
   Full card: https://gitnova.dev/en/r/Niko1221/Strata.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-02 11:06 UTC, updated every 30 minutes.