facebookresearch/metaseq

Integrate LucidRain's RotaryEmbeddings

Open

#621 opened on Jan 27, 2023

View on GitHub
 (2 comments) (0 reactions) (0 assignees)Python (701 forks)batch import
enhancementgood first issue

Repository metrics

Stars
 (6,195 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

See https://github.com/lucidrains/rotary-embedding-torch/blob/main/rotary_embedding_torch/rotary_embedding_torch.py

And from PaLM paper:

We use RoPE embeddings (Su et al., 2021) rather than absolute or relative position embeddings, since RoPE embeddings have been shown to have better performance on long sequence lengths.

Contributor guide

Research direction
Read the linked rotary embedding implementation and the PaLM paper. Locate where position embeddings are applied in the codebase (likely in attention modules) and replace them with RotaryEmbeddings. Ensure compatibility with existing model architectures.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchTransformer
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50