microsoft / microsoft/Tokenizer

Support Llama3.1 tokenization

Open
#56 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C#
Stars
213
Forks
37
Avg merge
5d 1h
Merged PRs (30d)
5

Description

Llama3.1's tokenizer is also BPE-based. We already ship this library in VS Code's Copilot Chat extension and it would be great if Llama3.1 was supported so that we do not need to ship another library.

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 by locating the existing BPE tokenizer implementation and its model-specific configuration for OpenAI LLMs. Determine what Llama3.1 tokenization data and behavior must be represented, then identify the relevant tests or add coverage for representative Llama3.1 inputs. Done means the library supports Llama3.1 without requiring another tokenizer library.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp, typescript
Domain
ai, machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.