diff --git a/slm/examples/machine_reading_comprehension/SQuAD/README.md b/slm/examples/machine_reading_comprehension/SQuAD/README.md
index 1afb2b027e56..60f5aa70e584 100644
--- a/slm/examples/machine_reading_comprehension/SQuAD/README.md
+++ b/slm/examples/machine_reading_comprehension/SQuAD/README.md
@@ -164,6 +164,7 @@ python -m paddle.distributed.launch --gpus "0" run_squad.py \
 
 在 Fine-tune 完成后，我们可以使用如下方式导出希望用来预测的模型：
 
+默认模型：
 ```shell
 python -u ./export_model.py \
     --model_type bert \
@@ -171,6 +172,14 @@ python -u ./export_model.py \
     --output_path ./infer_model/model
 ```
 
+微调模型：
+```shell
+python -u ./export_model.py \
+    --model_type bert \
+    --model_path tmp/squad/model_5000 \
+    --output_path ./infer_model/model
+```
+
 其中参数释义如下：
 - `model_type` 指示了模型类型，使用 BERT 模型时设置为 bert 即可。
 - `model_path` 表示训练模型的保存路径，与训练时的`output_dir`一致。
@@ -192,4 +201,83 @@ python -u deploy/python/predict.py \
 - `batch_size` 表示每个预测批次的样本数目。
 - `max_seq_length` 表示最大句子长度，超过该长度将被截断，和训练时一致。
 
+运行结果示例：
+```
+{
+  "exact": 37.74109323675567,
+  "f1": 42.348199704946815,
+  "total": 11873,
+  "HasAns_exact": 75.59041835357625,
+  "HasAns_f1": 84.81784330243481,
+  "HasAns_total": 5928,
+  "NoAns_exact": 0.0,
+  "NoAns_f1": 0.0,
+  "NoAns_total": 5945,
+  "best_exact": 50.11370336056599,
+  "best_exact_thresh": 0.0,
+  "best_f1": 50.11370336056599,
+  "best_f1_thresh": 0.0
+}
+```
+
 以上命令将在 SQuAD v1.1的验证集上进行预测。此外，同训练时一样，用户可以通过命令行传入`--version_2_with_negative`控制所需要的 SQuAD 数据集版本。
+
+### 其他问题
+#### Q1: 适配 python 3.8的 datasets 3.1.0无法支持当前任务
+如果运行时出现如下问题：
+
+>  File "/home/aistudio/.cache/huggingface/modules/datasets_modules/datasets/squad_v2/dca5ba0e483a42ca20ec41a13e9fb630541d6fcb0ba646da3e8ff9a1f21fcb81/squad_v2.py", line 19, in <module>
+>    from datasets.tasks import QuestionAnsweringExtractive
+> ModuleNotFoundError: No module named 'datasets.tasks'
+
+那么需要对 datasets 进行版本更换。运行：
+```shell
+pip install -U "datasets>=2.14.6,<3.0.0"
+```
+安装 ```datasets-2.21.0```等版本可以正常运行。
+
+
+#### Q2: 无法通过运行命令连接 huggingface 获取 SQuAD 数据集
+1. 手动从[数据集官网](https://rajpurkar.github.io/SQuAD-explorer/)下载 training/dev set 并放在当前目录。
+
+2. 将 ```run_squad.py```中的
+```python
+if args.version_2_with_negative:
+    train_examples = load_dataset("squad_v2", split="train", trust_remote_code=True)
+    dev_examples = load_dataset("squad_v2", split="validation", trust_remote_code=True)
+else:
+    train_examples = load_dataset("squad", split="train", trust_remote_code=True)
+    dev_examples = load_dataset("squad", split="validation", trust_remote_code=True)
+```
+替换为
+```python
+datasets = load_dataset(
+    "squad_v2",
+    data_files={
+        "train": "train-v2.0.json",
+        "validation": "dev-v2.0.json"
+    }
+)
+train_examples = datasets["train"]
+dev_examples = datasets["validation"]
+```
+
+3. 将 ```deploy/python/predict.py```中的
+```python
+if args.version_2_with_negative:
+    raw_dataset = load_dataset("squad_v2", split="validation")
+else:
+    raw_dataset = load_dataset("squad", split="validation")
+```
+替换为
+```python
+datasets = load_dataset(
+    "squad_v2",
+    data_files={
+        "train": "train-v2.0.json",
+        "validation": "dev-v2.0.json"
+    }
+)
+raw_dataset = datasets["validation"]
+```
+正常运行命令即可。
diff --git a/slm/examples/machine_reading_comprehension/SQuAD/deploy/python/predict.py b/slm/examples/machine_reading_comprehension/SQuAD/deploy/python/predict.py
index 3a8281d70d96..eb572818fa5d 100644
--- a/slm/examples/machine_reading_comprehension/SQuAD/deploy/python/predict.py
+++ b/slm/examples/machine_reading_comprehension/SQuAD/deploy/python/predict.py
@@ -21,6 +21,10 @@
 
 from paddlenlp.data import Dict, Pad
 from paddlenlp.metrics.squad import compute_prediction, squad_evaluate
+from paddlenlp.utils.env import (
+    PADDLE_INFERENCE_MODEL_SUFFIX,
+    PADDLE_INFERENCE_WEIGHTS_SUFFIX,
+)
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), os.pardir, os.pardir)))
 from args import parse_args  # noqa: E402
@@ -35,7 +39,10 @@ def __init__(self, predictor, input_handles, output_handles):
 
     @classmethod
     def create_predictor(cls, args):
-        config = paddle.inference.Config(args.model_name_or_path + ".pdmodel", args.model_name_or_path + ".pdiparams")
+        config = paddle.inference.Config(
+            args.model_name_or_path + f"{PADDLE_INFERENCE_MODEL_SUFFIX}",
+            args.model_name_or_path + f"{PADDLE_INFERENCE_WEIGHTS_SUFFIX}",
+        )
         if args.device == "gpu":
             # set GPU configs accordingly
             config.enable_use_gpu(100, 0)