[Model] Add support for BERT-like Chinese ERNIE pooling models (#36385)

Signed-off-by: whyiug <whyiug@hotmail.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>

tests/models/language/pooling/test_token_classification.py

@@ -25,11 +25,17 @@ def seed_everything():
     yield
 
 
-@pytest.mark.parametrize("model", ["boltuix/NeuroBERT-NER"])
+@pytest.mark.parametrize(
+    "model",
+    [
+        "boltuix/NeuroBERT-NER",
+        "gyr66/Ernie-3.0-base-chinese-finetuned-ner",
+    ],
+)
 # The float32 is required for this tiny model to pass the test.
 @pytest.mark.parametrize("dtype", ["float"])
 @torch.inference_mode
-def test_bert_models(
+def test_bert_like_models(
     hf_runner,
     vllm_runner,
     example_prompts,