OpenNMT / OpenNMT/CTranslate2

Support for `Alibaba-NLP/gte-multilingual-base`

Open
#1,879 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

Right now Alibaba-NLP/gte-multilingual-base is one of the best Encoders for retrieval, but unfortunately it's not supported right now

ct2-transformers-converter --model Alibaba-NLP/gte-multilingual-base --output_dir gte-multilingual-base-int8 --quantization int8 --trust_remote_code

Error

ValueError: No conversion is registered for the model configuration NewConfig (supported configurations are: BartConfig, BertConfig, BloomConfig, CamembertConfig, CodeGenConfig, DistilBertConfig, FalconConfig, GPT2Config, GPTBigCodeConfig, GPTJConfig, GPTNeoXConfig, Gemma2Config, GemmaConfig, LlamaConfig, M2M100Config, MBartConfig, MPTConfig, MT5Config, MarianConfig, MistralConfig, MixFormerSequentialConfig, OPTConfig, PegasusConfig, Phi3Config, PhiConfig, Qwen2Config, RWConfig, RobertaConfig, T5Config, Wav2Vec2BertConfig, Wav2Vec2Config, WhisperConfig, XLMRobertaConfig)

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

Reproduce the reported command for Alibaba-NLP/gte-multilingual-base and inspect the converter path implicated by the NewConfig error. Determine the model support needed, then verify that conversion completes with the shown int8 options instead of reporting an unregistered configuration.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, tooling
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.