Tiny fix of README (#548)

* add ernie_matching point-wise & pair-wise

* Rename some Class

* fix some typo

* add FewCLUE 9 datasets

* 1. Using ernie-gram to train ernie_matching point-wise & pair-wise
2. update README.md

* Tiny fix

* Tiny fix of README.md

Co-authored-by: yingyibiao <[email protected]>

Author: tianxin

examples/few_shot/efl/README.md

@@ -27,7 +27,7 @@ train_ds, dev_ds, public_test_ds = load_dataset("fewclue", name="tnews", splits=
 通过如下命令，指定 GPU 0 卡,  在 FewCLUE 的 `tnews` 数据集上进行训练&评估
 ```
 python -u -m paddle.distributed.launch --gpus "0" \
-    ptuning.py \
+    train.py \
     --task_name "tnews" \
     --device gpu \
     --negative_num 1 \

examples/text_matching/ernie_matching/README.md

@@ -57,21 +57,21 @@ python -u -m paddle.distributed.launch --gpus "0" train_pointwise.py \
 
 ```python
 
-# 使用 ernie-gram 预训练模型
+# 使用 ERNIE-Gram 预训练模型
 model = ppnlp.transformers.ErnieGramModel.from_pretrained('ernie-gram-zh')
 tokenizer = ppnlp.transformers.ErnieGramTokenizer.from_pretrained('ernie-gram-zh')
 
-# 使用ernie预训练模型
-# ernie
-#model = ppnlp.transformers.ErnieModel.from_pretrained('ernie'))
-#tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained('ernie')
+# 使用 ERNIE 预训练模型
+# ernie-1.0
+#model = ppnlp.transformers.ErnieModel.from_pretrained('ernie-1.0'))
+#tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained('ernie-1.0')
 
 # ernie-tiny
 # model = ppnlp.transformers.ErnieModel.from_pretrained('ernie-tiny'))
 # tokenizer = ppnlp.transformers.ErnieTinyTokenizer.from_pretrained('ernie-tiny')
 
 
-# 使用bert预训练模型
+# 使用 BERT 预训练模型
 # bert-base-chinese
 # model = ppnlp.transformers.BertModel.from_pretrained('bert-base-chinese')
 # tokenizer = ppnlp.transformers.BertTokenizer.from_pretrained('bert-base-chinese')
@@ -85,7 +85,7 @@ tokenizer = ppnlp.transformers.ErnieGramTokenizer.from_pretrained('ernie-gram-zh
 # tokenizer = ppnlp.transformers.BertTokenizer.from_pretrained('bert-wwm-ext-chinese')
 
 
-# 使用roberta预训练模型
+# 使用 RoBERTa 预训练模型
 # roberta-wwm-ext
 # model = ppnlp.transformers.RobertaModel.from_pretrained('roberta-wwm-ext')
 # tokenizer = ppnlp.transformers.RobertaTokenizer.from_pretrained('roberta-wwm-ext')

examples/text_matching/sentence_transformers/README.md

@@ -91,17 +91,17 @@ $ python -m paddle.distributed.launch --gpus "0" train.py --device gpu --save_di
 代码示例中使用的预训练模型是ERNIE，如果想要使用其他预训练模型如BERT，RoBERTa，Electra等，只需更换`model` 和 `tokenizer`即可。
 
 ```python
-# 使用ernie预训练模型
-# ernie
-model = ppnlp.transformers.ErnieModel.from_pretrained('ernie'))
-tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained('ernie')
+# 使用 ERNIE 预训练模型
+# ernie-1.0
+model = ppnlp.transformers.ErnieModel.from_pretrained('ernie-1.0'))
+tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained('ernie-1.0')
 
 # ernie-tiny
 # model = ppnlp.transformers.ErnieModel.from_pretrained('ernie-tiny'))
 # tokenizer = ppnlp.transformers.ErnieTinyTokenizer.from_pretrained('ernie-tiny')
 
 
-# 使用bert预训练模型
+# 使用 BERT 预训练模型
 # bert-base-chinese
 # model = ppnlp.transformers.BertModel.from_pretrained('bert-base-chinese')
 # tokenizer = ppnlp.transformers.BertTokenizer.from_pretrained('bert-base-chinese')
@@ -115,7 +115,7 @@ tokenizer = ppnlp.transformers.ErnieTokenizer.from_pretrained('ernie')
 # tokenizer = ppnlp.transformers.BertTokenizer.from_pretrained('bert-wwm-ext-chinese')
 
 
-# 使用roberta预训练模型
+# 使用 RoBERTa 预训练模型
 # roberta-wwm-ext
 # model = ppnlp.transformers.RobertaModel.from_pretrained('roberta-wwm-ext')
 # tokenizer = ppnlp.transformers.RobertaTokenizer.from_pretrained('roberta-wwm-ext')