Add lora test using qwen

[lucylq]

Summary

Use qwen0.6B with unsloth (instead of llama1B with torchtune) for lora test.

1. Smaller model / quicker test.
2. Eventually remove dependency on torchtune.
3. Qwen is not gated on HF.

TODO: add quantized test after #15951

Expected result prefix: 
<|im_start|>user Calculate 15% of 80?<|im_end|><|im_start|>assistant
To calculate 15% of 80, we can multiply 80 by 0.15.
80 * 0.15 = 12
So, 15% of 80 is 12.
#### 12
The answer is: 12<|im_end|>
+ echo 'Actual result: 
<|im_start|>user Calculate 15% of 80?<|im_end|><|im_start|>assistant
To calculate 15% of 80, we can multiply 80 by 0.15.
80 * 0.15 = 12
So, 15% of 80 is 12.
#### 12
The answer is: 12<|im_end|>

PyTorchObserver {"prompt_tokens":15,"generated_tokens":65,"model_load_start_ms":1765320124550,"model_load_end_ms":1765320127516,"inference_start_ms":1765320152867,"inference_end_ms":1765320178119,"prompt_eval_end_ms":1765320153334,"first_token_ms":1765320153334,"aggregate_sampling_time_ms":19,"SCALING_FACTOR_UNITS_PER_SECOND":1000}'
Actual result: 
<|im_start|>user Calculate 15% of 80?<|im_end|><|im_start|>assistant
To calculate 15% of 80, we can multiply 80 by 0.15.
80 * 0.15 = 12
So, 15% of 80 is 12.
#### 12
The answer is: 12<|im_end|>

PyTorchObserver {"prompt_tokens":15,"generated_tokens":65,"model_load_start_ms":1765320124550,"model_load_end_ms":1765320127516,"inference_start_ms":1765320152867,"inference_end_ms":1765320178119,"prompt_eval_end_ms":1765320153334,"first_token_ms":1765320153334,"aggregate_sampling_time_ms":19,"SCALING_FACTOR_UNITS_PER_SECOND":1000}
+ echo Success
Success

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16161

• 📄 Preview Python docs built from this PR

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

⏳ No Failures, 191 Pending

As of commit 84d40b3 with merge base 56e131b ():
💚 Looks good so far! There are no failures yet. 💚

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[larryliu0820]

Remove this? Seems out dated

[larryliu0820]

try make llama-cpu