hook up hf + moe + nvfp4 script to lm_eval

[vkuzo]

Summary:

Adds a very simple lm_eval call to the hf + moe + nvfp4 example script.
With a small fix in the transformers repo
(huggingface/transformers#45609), it works!

The script itself is throwaway, just a proof that things work e2e on
single GPU.

Test Plan:

> time python scripts/prototype/test_nvfp4_moe.py --recipe=bf16 --run_lm_eval

| Tasks  |Version|Filter|n-shot|    Metric     |   |Value |   |Stderr|
|--------|------:|------|-----:|---------------|---|-----:|---|------|
|wikitext|      2|none  |     0|bits_per_byte  |↓  |0.5895|±  |   N/A|
|        |       |none  |     0|byte_perplexity|↓  |1.5047|±  |   N/A|
|        |       |none  |     0|word_perplexity|↓  |8.8910|±  |   N/A|

real    0m37.922s

> time python scripts/prototype/test_nvfp4_moe.py --recipe=nvfp4 --run_lm_eval

| Tasks  |Version|Filter|n-shot|    Metric     |   |Value |   |Stderr|
|--------|------:|------|-----:|---------------|---|-----:|---|------|
|wikitext|      2|none  |     0|bits_per_byte  |↓  |0.6024|±  |   N/A|
|        |       |none  |     0|byte_perplexity|↓  |1.5183|±  |   N/A|
|        |       |none  |     0|word_perplexity|↓  |9.3277|±  |   N/A|

real    0m32.234s

[vkuzo]

Stack from ghstack (oldest at bottom):

• install debug expert token counters on nvfp4 moe test script #4322
• -> hook up hf + moe + nvfp4 script to lm_eval #4321

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/4321

• 📄 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:

• Rolling out OSDC (ARC) runners on pull & trunk workflows in PyTorch main

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