Lightning-AI / Lightning-AI/litgpt

[Tokenizer Question]: Falcon 7B fine-tune with new language

Open
#225 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

help wanted question
Dominant language
Python
Stars
13.7k
Forks
1.5k
Avg merge
15h 37m
Merged PRs (30d)
1

Description

Hi there,

Currently, I'm attempting to fine-tune a customer dataset that includes Chinese text.

During the fine-tuning process, I noticed that although the tokenizer functions during training, I did not observe any parameter increase from token embedding in the initial information. I'm wondering if I should add new tokens that are not present in falcon-7b/tokenizer.json to the tokenizer and model.

Could you please provide me with some guidance on how to add tokens and modify the token embedding in Falcon-7B? (If necessary)

Many thanks :-)

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

No files, tests, or entry points are named. Start by locating the Falcon 7B tokenizer and model configuration, then establish whether the requested vocabulary and embedding changes are required; done would be a documented, project-aligned answer or a clearly scoped implementation plan.

Written by the indexing model from the issue text.

Assessment

Domain
ai, 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.