[Feature]: make token count accessible without loading the model
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.2k
- Forks
- 248
- Avg merge
- 4d 8h
- Merged PRs (30d)
- 4
Description
What feature would you like to request?
The new token_count method currently requires a model to be loaded before using it.
However, the better approach might be to allow loading just a tokenizer without loading a model
Is there any additional information you would like to provide?
No response
Contributor guide
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
Start by tracing the existing token_count method and the model-loading path to identify where tokenizer loading is coupled to model loading. Done means callers can obtain token counts with only a tokenizer loaded, without requiring the embedding model.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100