diff --git a/.github/workflows/ci_eval.yaml b/.github/workflows/ci_eval.yaml
index 0c10fe2a5..273bfe3ef 100644
--- a/.github/workflows/ci_eval.yaml
+++ b/.github/workflows/ci_eval.yaml
@@ -67,11 +67,7 @@ jobs:
             iree-runtime \
             "numpy<2.0"
       - name: Run perplexity test with vmfb
-        run:  pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_vmfb_test.py --longrun \
-              --iree-device='hip://7' \
-              --iree-hip-target='gfx942' \
-              --llama3-8b-f16-model-path=/data/llama-3.1/8b/llama8b_f16.irpa \
-              --llama3-8b-tokenizer-path=/data/llama-3.1/8b/tokenizer_config.json
+        run:  pytest -n 8 -v -s sharktank/tests/evaluate/perplexity_vmfb_test.py --longrun --iree-device='hip://7' --iree-hip-target='gfx942' --llama3-8b-f16-model-path=/data/llama-3.1/8b/llama8b_f16.irpa --llama3-8b-tokenizer-path=/data/llama-3.1/8b/tokenizer_config.json
 
   # test_perplexity_torch:
   #   timeout-minutes: 1000