NextTransformer

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.

Interactive-Active-AI/NextTransformer

View on GitHub ↗

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.

NextTransformer ranks 126th of 370 in Training Toolkits, actively maintained, last commit 2 days ago.

Star trajectory

18 days tracked
2026-11-04489 stars today2026-11-22
Momentum

- in 30d, below the Training Toolkits median of +0.3%.

Maintenance

Last commit 2 days ago, fresher than the median of 199.5d.

How it compares in Training Toolkits

NextTransformer
489
stars
- 30d
commit 2 days ago
Training Toolkits median
320
stars
+0.3% 30d
commit ~199.5d ago
Leader · TTS
46.3k
stars
+0.3% 30d
commit 827 days ago

Ranked 126th of 370 by stars.

Ranked by shared tags, then keywords, then stars
  1. [𝗜𝗖𝗠𝗟 𝟮𝟬𝟮𝟲] Dispersion loss counteracts embedding condensation and improves generalization in small…

    +7 (+5.7%) in 30d · Committed 153d ago · Python · Other license

    Shares Pretraining & Training, Training Toolkits, Interpretability & Alignment

  2. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Training Toolkits, Pretraining & Training, Interpretability & Alignment

  3. A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a…

    +550 (+79%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Pretraining & Training, Interpretability & Alignment

  4. Projects from basic algorithms to MARL. Implements MADDPG,MATD3,MA/HAPPO in Predator-Prey pursuit games with…

    +9 (+2.0%) in 30d · Committed 103d ago · Jupyter Notebook · MIT

    Shares Training Toolkits, Pretraining & Training

  5. Research infrastructure for understanding, testing, and modifying SAE features in LLMs.

    Committed today · Python · Apache-2.0

    Shares Interpretability & Alignment, Training Toolkits

  6. A from-scratch, dependency-free GPT implementation in pure NumPy: byte-level tokenizer, multi-head…

    Committed 16d ago · Python · MIT

    Shares Pretraining & Training, Training Toolkits

  7. [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior…

    +2 (+0.2%) in 30d · Committed 760d ago · Python · Apache-2.0

    Shares Training Toolkits, Interpretability & Alignment

  8. Building DeepSeek R1 from Scratch

    +9 (+1.1%) in 30d · Committed 5d ago · Jupyter Notebook · MIT

    Shares Training Toolkits, Pretraining & Training

  9. A next-generation automatic algorithm design platform, making automated algorithm design more accessible and…

    +49 (+7.3%) in 30d · Committed today · Python · BSD-3-Clause

    Shares Training Toolkits, Interpretability & Alignment

  10. [ICML 2026 & EMNLP 2026] Multimodal deep-research MLLM and benchmark. The first long-horizon multimodal…

    +5 (+0.7%) in 30d · Committed 105d ago · Python · MIT

    Shares Pretraining & Training, Interpretability & Alignment

Language
Python
License
MIT License
Contributors
13
Forks
42
Watchers
17
Open issues
12
Releases
0
Created
2026-10-31
Stars this week
+75

You've seen where NextTransformer stands today.

Get the moves before everyone else: the 5 Training Toolkits repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain NextTransformer?

Claim this page to add your own call-to-action.

Claim this page