microsoft / microsoft/ai-dev-gallery

[SAMPLE]How to use the model "intfloat/multilingual-e5-small" to complete the embedding operation

Open
#352 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

sample
Dominant language
C#
Stars
1.5k
Forks
223
PR merge metrics
No merged PRs in 30d

Description

I need to use the intfloat/multilingual-e5-small model. However, I encountered a problem with missing tags such as [UNK] and [SEP] when loading VOCab.txt on the ARM64 architecture. Upon researching, it was found that 'intfloat/multilingual-e5-small' uses XLMRobertaTokenizer (dependent on SentencePiece). I am in Microsoft I found SentencePieceTokenizers in ML.Tokenizers, and their usage is different from BertTokenizer's. I don't know how to use it. Can you provide me with a tutorial on how to use it. I went through the file The OpenRead method read the Stream and successfully loaded SentencePieceTokenizers, but I don't know how to use it in the future.

Contributor guide

No contributing guide indexed for this repository

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 reviewing the OpenRead method and the SentencePieceTokenizers usage in ML.Tokenizers, then verify how the intfloat/multilingual-e5-small model is loaded on ARM64. Done means a documented tutorial showing how to use the loaded tokenizer for the embedding workflow and addressing the missing [UNK] and [SEP] tags.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.