meta-pytorch / meta-pytorch/executorch-examples

[qnn example support] `Invalid model type category: 4` which means the qnn does't support?

Open
#227 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Kotlin
Stars
83
Forks
30
Avg merge
3d 9h
Merged PRs (30d)
2

Description

Hello Teams,

I follow the this executorch to build the model, and run the model successful on the qualcomm cheipset (SA8295). I hope to build the android app following by this qualcomm readme, but found the error from the chat box:

Model load failure: [Executorch Error 0x12] Invalid argument: Invalid model type category: 4. Valid values are: 1 or 2

from the src code, qnn model is type 4.

BTW, does this demo app support the tokenizer.json rather than tokenizer.model/.bin? for example Qwen models.

Hope you can give me some advice.

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 with ModelUtils.kt at line 28 and the Qualcomm README, then compare the app's expected model type with the reported category 4 error. Verify whether tokenizer.json is covered alongside tokenizer.model/.bin, and document the supported inputs or required app change.

Written by the indexing model from the issue text.

Assessment

Tech stack
android, kotlin, pytorch
Domain
machine-learning, mobile
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.