JoeLi12345 / nGPTLinks
an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)
☆109Updated 10 months ago
Alternatives and similar repositories for nGPT
Users that are interested in nGPT are comparing it to the libraries listed below
Sorting:
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 9 months ago
- look how they massacred my boy☆63Updated last year
- DeMo: Decoupled Momentum Optimization☆198Updated last year
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆59Updated 3 months ago
- Collection of autoregressive model implementation☆85Updated 2 weeks ago
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆175Updated last year
- ☆137Updated last year
- MoE training for Me and You and maybe other people☆331Updated 3 weeks ago
- Train your own SOTA deductive reasoning model☆107Updated 10 months ago
- EvaByte: Efficient Byte-level Language Models at Scale☆115Updated 9 months ago
- A collection of lightweight interpretability scripts to understand how LLMs think☆89Updated last week
- working implimention of deepseek MLA☆45Updated last year
- An introduction to LLM Sampling☆79Updated last year
- Simple Transformer in Jax☆142Updated last year
- PyTorch implementation of models from the Zamba2 series.☆186Updated last year
- Simple & Scalable Pretraining for Neural Architecture Research☆307Updated last month
- H-Net Dynamic Hierarchical Architecture☆81Updated 4 months ago
- Plotting (entropy, varentropy) for small LMs☆99Updated 8 months ago
- ☆27Updated last year
- Storing long contexts in tiny caches with self-study☆231Updated last month
- NanoGPT (124M) quality in 2.67B tokens☆28Updated 4 months ago
- Lego for GRPO☆30Updated 8 months ago
- Exploring Applications of GRPO☆251Updated 5 months ago
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.☆18Updated 6 months ago
- smolbox of recipies☆29Updated 9 months ago
- ☆66Updated 10 months ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆251Updated last year
- Scaling is a distributed training library and installable dependency designed to scale up neural networks, with a dedicated module for tr…☆66Updated 2 months ago
- The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in languag…☆127Updated 3 months ago