microsoft / microsoft/debug-gym
Tokenizer for Claude models
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 307
- Forks
- 45
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 9
Description
The current way of trimming strings and messages are quite hacky, partly because we don't have access to Claude's tokenizer (we do for OAI models). Once we find good tokenizers for claude models, we will need to revisit the trimming functions.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue does not name a file, test, or entry point. Start by locating the trimming functions and how tokenizers are used for OpenAI models, then investigate suitable tokenizers for Claude models. Done means selecting an appropriate Claude tokenizer and revisiting the string and message trimming behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100