Support for Huggingface safetensors and tokenizer.json for LLM exporting
Open
Nobody has claimed this yet.
enhancement
module: exir
triaged
- Dominant language
- Python
- Stars
- 5k
- Forks
- 1.2k
- Avg merge
- 2d 10h
- Merged PRs (30d)
- 581
Description
🚀 The feature, motivation and pitch
Currently, one has to manually convert model*.safetensors to checkpoint.pth before utilizing executorch's export. Perhaps there should be support for safetensor files right out the box?
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
cc @JacobSzwejbka @angelayi
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
The issue names no files, tests, or entry points. Start by locating the existing Executorch export path that requires model*.safetensors conversion to checkpoint.pth, then determine how safetensors and tokenizer.json should enter that flow. Done means LLMs can be exported directly without the manual conversion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100