Export Stories110M model to compare on-device numerics

[navsud]

Summary:

• Replace inf (-inf) to 64k (-64k) as we use int16 for activations.
• For int16 activations, "MinMaxObserver" is recommended, updated quantizer to reflect this change.

Repro command:
python -m executorch.examples.models.llama.export_llama --disable_dynamic_shape --qnn --pt2e_quantize qnn_16a4w -v -kv -p ~/pllm/stories110M/params.json -c ~/pllm/stories110M/stories_110M.pt --soc_model SM8650 -n ~/pllm/stories110M/exported_models/sm8650.pte --max_seq_len 512 --tokenizer_path ~/pllm/stories110M/tokenizer.model 2>&1 | tee ~/pllm/stories110M/exported_models/export_log.txt

Differential Revision: D66037630

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/6939

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❗ 1 Active SEVs

There are 1 currently active SEVs. If your PR is affected, please view them below:

• [DomainsOnly] Jobs fail with GLIBC version not found

❌ 2 New Failures

As of commit ad5c992 with merge base a0ac820 ():

NEW FAILURES - The following jobs have failed:

• Lint / lintrunner / linux-job (gh)
  >>> Lint for extension/llm/export/builder.py:
• pull / test-llava-runner-linux / linux-job (gh)
  test_llava_export

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[facebook-github-bot]

This pull request was exported from Phabricator. Differential Revision: D66037630

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.

[github-actions]

Looks like this PR hasn't been updated in a while so we're going to go ahead and mark this as Stale.
Feel free to remove the Stale label if you feel this was a mistake.
If you are unable to remove the Stale label please contact a maintainer in order to do so.
If you want the bot to never mark this PR stale again, add the no-stale label.
Stale pull requests will automatically be closed after 30 days of inactivity.