cloneofsimo / ezmupLinks
Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam
☆84Updated last year
Alternatives and similar repositories for ezmup
Users that are interested in ezmup are comparing it to the libraries listed below
Sorting:
- These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning☆48Updated last year
- WIP☆93Updated 11 months ago
- supporting pytorch FSDP for optimizers☆84Updated 7 months ago
- ☆53Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆130Updated last year
- ☆34Updated 10 months ago
- ☆83Updated last year
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆55Updated 4 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆149Updated last month
- ☆81Updated last year
- Mixture of A Million Experts☆46Updated last year
- Language models scale reliably with over-training and on downstream tasks☆97Updated last year
- Automatically take good care of your preemptible TPUs☆36Updated 2 years ago
- LoRA for arbitrary JAX models and functions☆140Updated last year
- Efficient optimizers☆252Updated last week
- ☆64Updated 8 months ago
- ☆23Updated last year
- Focused on fast experimentation and simplicity☆76Updated 7 months ago
- ☆30Updated 8 months ago
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆54Updated last year
- Implementation of Infini-Transformer in Pytorch☆111Updated 7 months ago
- Pytorch implementation of the PEER block from the paper, Mixture of A Million Experts, by Xu Owen He at Deepmind☆127Updated 11 months ago
- ☆114Updated last year
- ☆115Updated last month
- Flexibly track outputs and grad-outputs of torch.nn.Module.☆13Updated last year
- ☆53Updated last year
- Train vision models using JAX and 🤗 transformers☆98Updated 3 months ago
- Implementation of the Llama architecture with RLHF + Q-learning☆166Updated 6 months ago
- Sparse Autoencoders for Stable Diffusion XL models.☆69Updated last week
- ☆53Updated 10 months ago