diff --git a/src/maxtext/layers/nnx_decoders.py b/src/maxtext/layers/nnx_decoders.py
index 1a9fdd48b0..bfb942d85d 100644
--- a/src/maxtext/layers/nnx_decoders.py
+++ b/src/maxtext/layers/nnx_decoders.py
@@ -438,7 +438,7 @@ def __init__(
     self.is_gemma4 = self.config.decoder_block == DecoderBlockType.GEMMA4
     self.is_gemma4_small = self.config.decoder_block == DecoderBlockType.GEMMA4_SMALL
 
-    if config.mhc_expansion_rate > 1 and config.decoder_block == DecoderBlockType.DEEPSEEK4:
+    if getattr(config, "mhc_expansion_rate", 1) > 1 and config.decoder_block == DecoderBlockType.DEEPSEEK4:
       self.hc_head = mhc.DeepSeek4HyperHead(
           config=config,
           mesh=self.mesh,
diff --git a/tests/utils/forward_pass_logit_checker.py b/tests/utils/forward_pass_logit_checker.py
index a51b23980f..6b79e0ae02 100644
--- a/tests/utils/forward_pass_logit_checker.py
+++ b/tests/utils/forward_pass_logit_checker.py
@@ -379,6 +379,12 @@ def main(config, test_args):  # pylint: disable=W0621
     try:
       max_logging.log(f"Loading tokenizer from {path}.")
       tokenizer = AutoTokenizer.from_pretrained(path, token=hf_token, trust_remote_code=test_args.trust_remote_code)
+      # Mistral and Llama tokenizers ship no pad token, and the calls below pass padding=True, which
+      # transformers refuses without one ("Asking to pad but the tokenizer does not have a padding
+      # token"). Prompts are tokenized one at a time here, so nothing is ever actually padded and
+      # borrowing eos changes no result -- it only satisfies the check that rejects the call.
+      if tokenizer.pad_token is None:
+        tokenizer.pad_token = tokenizer.eos_token
       break
     except Exception as e:  # pylint: disable=broad-except,broad-exception-caught
       last_exception = e