pytorch / pytorch/executorch

Support for Huggingface safetensors and tokenizer.json for LLM exporting

Open
#7,696 3 comments 1 reaction 0 assignees View on GitHub

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

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

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.