[tests] Update lm_eval VL tests to qwen 3

[brian-dellabetta]

SUMMARY:
Upgrade the lm_eval vision languge tests from Qwen 2.5 to Qwen 3. After updating to include apply_chat_template, the scores closely align with what was achieved with Qwen 2.5

Prerequisites

• * [Deps] pin cmarkgfm until build issue resolved #1952

TEST PLAN:
The 3 lm_eval VL tests were run, and the accuracies were updated. Dense model achieves 0.833, all compressed models achieve 0.833 or 0.800

[github-actions]

👋 Hi! Thank you for contributing to llm-compressor. Please add the ready label when the PR is ready for review.

Note: This is required to complete the testing suite, please only add the label once the PR is code complete and local testing has been performed.

[dsikka]

Why not just use mmmu_val instead of the literature task? This gives us around 0.53 for the dense model?

[brian-dellabetta]

Why not just use mmmu_val instead of the literature task? This gives us around 0.53 for the dense model?

mmmu_val is 900 evals total instead of 30. that would add probably ~40 minutes to each lm-eval run, and we run two for each config, so total test time would increase over 3 hours with that change

[dsikka]

Why not use mmmu_val

Why not just use mmmu_val instead of the literature task? This gives us around 0.53 for the dense model?

mmmu_val is 900 evals total instead of 30. that would add probably ~40 minutes to each lm-eval run, and we run two for each config, so total test time would increase over 3 hours with that change

The 30 datapoints has proven to be very noisy historically. A happy medium might be better but we should also just validate the runtime for batch size of 100