lucidrains / PaLM-jax
Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)
☆187Updated 2 years ago
Alternatives and similar repositories for PaLM-jax:
Users that are interested in PaLM-jax are comparing it to the libraries listed below
- Implementation of Flash Attention in Jax☆206Updated last year
- ☆67Updated 2 years ago
- JAX implementation of the Llama 2 model☆216Updated last year
- ☆339Updated 11 months ago
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- Inference code for LLaMA models in JAX☆116Updated 9 months ago
- Amos optimizer with JEstimator lib.☆81Updated 9 months ago
- Train very large language models in Jax.☆203Updated last year
- ☆165Updated last year
- ☆184Updated 2 weeks ago
- some common Huggingface transformers in maximal update parametrization (µP)☆80Updated 2 years ago
- JAX Synergistic Memory Inspector☆168Updated 7 months ago
- JMP is a Mixed Precision library for JAX.☆193Updated last month
- Experiments around a simple idea for inducing multiple hierarchical predictive model within a GPT☆209Updated 6 months ago
- ☆58Updated 3 years ago
- LoRA for arbitrary JAX models and functions☆135Updated last year
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆236Updated last year
- HomebrewNLP in JAX flavour for maintable TPU-Training☆48Updated last year
- Exploring finetuning public checkpoints on filter 8K sequences on Pile☆115Updated last year
- Implementation of the conditionally routed attention in the CoLT5 architecture, in Pytorch☆226Updated 6 months ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆81Updated last year
- Automatically take good care of your preemptible TPUs☆36Updated last year
- ☆220Updated last month
- Named tensors with first-class dimensions for PyTorch☆321Updated last year
- Implementation of Mega, the Single-head Attention with Multi-headed EMA architecture that currently holds SOTA on Long Range Arena☆204Updated last year
- A simple library for scaling up JAX programs☆134Updated 4 months ago
- ☆67Updated 2 years ago
- A minimal PyTorch Lightning OpenAI GPT w DeepSpeed Training!☆111Updated last year
- Implementation of a Transformer, but completely in Triton☆259Updated 2 years ago
- Train vision models using JAX and 🤗 transformers☆96Updated last month