OpenNMT / OpenNMT/CTranslate2

[Feature Request] Support Epsilon Sampling

Open
#1,681 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement
Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

Epsilon sampling is a compelling alternative/complement to top_p and top_k sampling and would make a good addition to CTranslate2: https://arxiv.org/abs/2305.09860

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the linked Epsilon Sampling paper and comparing its proposal with the existing top_p and top_k sampling behavior in CTranslate2. Done means defining the integration scope and supporting Epsilon Sampling alongside those existing options, with validation that the behavior matches the paper.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.