cat-state / tinyparLinks
โ20Updated 2 years ago
Alternatives and similar repositories for tinypar
Users that are interested in tinypar are comparing it to the libraries listed below
Sorting:
- Large scale 4D parallelism pre-training for ๐ค transformers in Mixture of Experts *(still work in progress)*โ87Updated last year
- โ49Updated last year
- โ62Updated 3 years ago
- โ89Updated last year
- Experiment of using Tangent to autodiff tritonโ81Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Trainingโ50Updated last year
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limitโ63Updated 2 years ago
- A set of Python scripts that makes your experience on TPU betterโ54Updated 2 weeks ago
- Fast, Modern, and Low Precision PyTorch Optimizersโ112Updated last month
- Exploring finetuning public checkpoints on filter 8K sequences on Pileโ116Updated 2 years ago
- A fusion of a linear layer and a cross entropy loss, written for pytorch in triton.โ70Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ132Updated last year
- A toolkit for scaling law research โโ52Updated 8 months ago
- โ122Updated last year
- โ19Updated 4 months ago
- โ53Updated last year
- some common Huggingface transformers in maximal update parametrization (ยตP)โ82Updated 3 years ago
- JAX implementation of the Llama 2 modelโ218Updated last year
- A place to store reusable transformer components of my own creation or found on the interwebsโ60Updated 2 weeks ago
- Triton Implementation of HyperAttention Algorithmโ48Updated last year
- โ82Updated last year
- An implementation of the Llama architecture, to instruct and delightโ21Updated 4 months ago
- Experiments for efforts to train a new and improved t5โ76Updated last year
- Train a SmolLM-style llm on fineweb-edu in JAX/Flax with an assortment of optimizers.โ19Updated 2 months ago
- โ46Updated last year
- Automatically take good care of your preemptible TPUsโ36Updated 2 years ago
- Official repository for the paper "Approximating Two-Layer Feedforward Networks for Efficient Transformers"โ38Updated 3 months ago
- Code repository for the c-BTM paperโ107Updated 2 years ago
- QLoRA with Enhanced Multi GPU Supportโ37Updated 2 years ago
- Easily run PyTorch on multiple GPUs & machinesโ47Updated 3 months ago