OpenNMT / OpenNMT/CTranslate2

Missing converter : XLMRobertaFlashConfig

Open
#1,790 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Hello,

jinaai/jina-reranker-v2-base-multilingual uses a configuration_xlm_roberta.XLMRobertaFlashConfig architecture which seems to be defined there

When trying to quantize the model with CTranslate2 obviously it says XLMRobertaFlashConfig converter is missing.

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 with the linked config.json for jinaai/jina-reranker-v2-base-multilingual and the linked xlm-roberta-flash-implementation to understand XLMRobertaFlashConfig. Trace how CTranslate2 reports a missing converter when quantization is attempted, then verify that the model can be quantized successfully once support is present.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, huggingface
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.