qlabs-eng/noise
Can I trust it?
Worth a closer look before you use it.
Warnings Check
Very new: it was created 8 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 pretraining speedrun for language model learning algorithms that never run a backward pass. It fixes a 37.7M-parameter transformer, a 10M-token FineWeb training set and a validation cross-entropy score, and compares forward-only, non-backprop methods on validation loss and…
Who it's for
Researchers and ML engineers studying gradient-free or forward-only learning algorithms for language model pretraining
How to use it
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up qlabs-eng/noise in my project. Follow its README: https://github.com/qlabs-eng/noise. 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.
18,268 GitHub repos watched and ranked every hour. Figures as of 20 October 2026.
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/qlabs-eng/noise?ref=badge)Similar repos
- inclusionAI/Ming-3.0-tts
Multilingual text-to-speech models (0.5b dense and tiny MoE) with voice cloning, voice design from text, built-in voices, natural-language delivery instructions and inline paralinguistic tags such as
- NVlabs/ASPIRE
A research framework for robotics in which language-model coding agents discover and refine sensorimotor skills through iterative debugging and evolutionary search, instead of gradient-based training.
- zzzz7788990213-ops/EvoVLM
Research code for LLM-guided evolutionary search over vision-language inference programs. It mutates prompts, image preprocessing, generation budgets and answer extraction for a frozen Qwen3-VL-2B mod
- HazyResearch/ncm
Research code for Next-Concept Modeling, a two-stage framework for parallel text generation. A multiscale residual VQ tokenizer encodes a sequence as a hierarchy of discrete codes, and a transformer p
- prabanta-dev/janas
A C inference engine for running large mixture-of-experts language models on ordinary computers, with or without a GPU. Weights stay on disk, and the experts each token needs are streamed from an NVMe
- Tencent-Hunyuan/Prism
Research code for Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K resolution. It partitions tokens into spatiotemporal zones and adapts bloc