MaartenGr / MaartenGr/BERTopic

Representation models using adapters

Open
#1,498 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
7.8k
Forks
920
Avg merge
22h 24m
Merged PRs (30d)
5

Description

Hi there,

The more I experiment, the clearer it becomes that most LLMs excel primarily, if not exclusively, in English. With the increasing demand for topic modeling in non-English languages, I'm curious if there's a way to integrate instruction-tuned adapters with Llama 2 in BERTopic. That would be a fantastic addition!

I appreciate the fantastic work you're doing.

Cheers,

Andrea

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

The issue does not name files, tests, or an entry point. Start by locating BERTopic's representation-model integration and reviewing how Llama 2 and instruction-tuned adapters would fit into it. Done would mean a defined, tested way to use such adapters for non-English topic modeling.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
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.