an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
☆111Mar 7, 2025Updated last year
Alternatives and similar repositories for nGPT
Users that are interested in nGPT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Post-trained LLaDA model with dynamic step scheduling☆35Mar 4, 2025Updated last year
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Apr 22, 2025Updated last year
- Code for the paper "Function-Space Learning Rates"☆24Jun 3, 2025Updated 11 months ago
- lossily compress representation vectors using product quantization☆59Oct 28, 2025Updated 6 months ago
- Simple GRPO scripts and configurations.☆59Feb 6, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆22Aug 27, 2023Updated 2 years ago
- Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse …☆1,224May 18, 2026Updated last week
- https://hf.co/hexgrad/Kokoro-82M☆14Jan 14, 2026Updated 4 months ago
- ☆15Feb 23, 2026Updated 3 months ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆57Mar 10, 2025Updated last year
- Code for the note "NF4 Isn't Information Theoretically Optimal (and that's Good)☆21Jun 22, 2023Updated 2 years ago
- DeMo: Decoupled Momentum Optimization☆201Dec 2, 2024Updated last year
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆31May 19, 2025Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆42Dec 29, 2025Updated 4 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code☆10Aug 29, 2023Updated 2 years ago
- ☆63Apr 8, 2026Updated last month
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated 8 months ago
- Lego for GRPO☆30May 27, 2025Updated 11 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆192Jan 19, 2026Updated 4 months ago
- Gradio chat interface for FastMLX☆12Sep 22, 2024Updated last year
- ☆69Mar 21, 2025Updated last year
- qwen3 experiments☆34Jul 1, 2025Updated 10 months ago
- Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs☆212Dec 4, 2025Updated 5 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- smolLM with Entropix sampler on pytorch☆149Oct 31, 2024Updated last year
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆91Mar 18, 2025Updated last year
- Supporting code for "LLMs for your iPhone: Whole-Tensor 4 Bit Quantization"☆11Mar 31, 2024Updated 2 years ago
- Setting up Vscode to work with Pytorch in C/C++ with CUDA support☆25Feb 5, 2025Updated last year
- Normalized Transformer (nGPT)☆207Nov 19, 2024Updated last year
- ☆24Nov 19, 2024Updated last year
- ☆33Nov 4, 2024Updated last year
- supporting pytorch FSDP for optimizers☆84Dec 8, 2024Updated last year
- Model code for inferencing T5☆66Mar 10, 2025Updated last year
- 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.
- ☆14Apr 7, 2022Updated 4 years ago
- ☆21May 26, 2024Updated 2 years ago
- ☆34Sep 10, 2024Updated last year
- Grokking on modular arithmetic in less than 150 epochs in MLX☆15Oct 24, 2024Updated last year
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆359Feb 17, 2026Updated 3 months ago
- II-Thought-RL is our initial attempt at developing a large-scale, multi-domain Reinforcement Learning (RL) dataset☆31Apr 8, 2025Updated last year
- An unofficial implementation of the Infini-gram model proposed by Liu et al. (2024)☆33Jun 19, 2024Updated last year