logging output fix

tests/llmcompressor/transformers/sparsification/test_compress_tensor_utils.py

@@ -1,3 +1,4 @@
+import logging
 import math
 import shutil
 
@@ -62,16 +63,26 @@ def test_sparse_model_reload(compressed, config, dtype, tmp_path):
         clear_sparse_session=False,
     )
 
+    # temporarily set the log level to error, to ignore printing out long missing
+    # and unexpected key error messages (these are EXPECTED for quantized models)
+    transformers_logger = logging.getLogger("transformers.modeling_utils")
+    restore_log_level = transformers_logger.getEffectiveLevel()
+    transformers_logger.setLevel(level=logging.ERROR)
+
     model = AutoModelForCausalLM.from_pretrained(
         tmp_path / "oneshot_out", torch_dtype=dtype
     )
 
+    # restore transformers logging level now that model shell is loaded
+    transformers_logger.setLevel(level=restore_log_level)
+
     # assert that sample layer has the intended sparsity
     assert math.isclose(
         tensor_sparsity(model.state_dict()[one_of_sparse_weights]),
         expected_sparsity,
         rel_tol=1e-3,
     )
+
     inferred_structure = SparsityConfigMetadata.infer_sparsity_structure()
     assert inferred_structure == "0:0"