Update README.md

README.md

@@ -21,11 +21,11 @@ Good at solving text summarization tasks, after fine-tuning on multiple Chinese
 
 |  需求 Demand  | 任务 Task       | 系列 Series      | 模型 Model    | 参数 Parameter | 额外 Extra |
 |  :----:  | :----:  | :----:  | :----:  | :----:  | :----:  |
-| 通用 General | 自然语言转换 NLT | 燃灯 Randeng | PEFASUS |      238M      |    文本摘要任务-中文 Summary-Chinese    |
+| 通用 General | 自然语言转换 NLT | 燃灯 Randeng | Deltalm |      362M      |    翻译任务 Zh-En    |
 
 ## 模型信息 Model Information
 
-参考论文：[PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization](https://arxiv.org/pdf/1912.08777.pdf)
+参考论文：[DeltaLM: Encoder-Decoder Pre-training for Language Generation and Translation by Augmenting Pretrained Multilingual Encoders](https://arxiv.org/pdf/2106.13736v2.pdf)
 
 ### 下游效果 Performance
 
@@ -36,20 +36,20 @@ Good at solving text summarization tasks, after fine-tuning on multiple Chinese
 ## 使用 Usage
 
 ```python
-from transformers import PegasusForConditionalGeneration,BertTokenizer
-# Need to download tokenizers_pegasus.py and other Python script from Fengshenbang-LM github repo in advance,
-# or you can download tokenizers_pegasus.py and data_utils.py in https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M/tree/main
+from transformers import AutoTokenizer
+# Need to download modeling_deltalm.py from Fengshenbang-LM github repo in advance,
+# or you can download modeling_deltalm.py in 
 # Strongly recommend you git clone the Fengshenbang-LM repo:
 # 1. git clone https://github.com/IDEA-CCNL/Fengshenbang-LM
-# 2. cd Fengshenbang-LM/fengshen/examples/translation/
-# and then you will see the tokenizers_pegasus.py and data_utils.py which are needed by pegasus model
+# 2. cd Fengshenbang-LM/fengshen/examples/deltalm/
+# and then you will see the modeling_deltalm.py which are needed by deltalm model
 
-from tokenizers_pegasus import PegasusTokenizer
+from modeling_deltalm import DeltalmForConditionalGeneration
 
-model = PegasusForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Pegasus-238M-Summary-Chinese")
-tokenizer = PegasusTokenizer.from_pretrained("IDEA-CCNL/Randeng-Pegasus-238M-Summary-Chinese")
+model = DeltalmForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-Deltalm-362M-Zh-En")
+tokenizer = AutoTokenizer.from_pretrained("microsoft/infoxlm-base")
 
-text = "在北京冬奥会自由式滑雪女子坡面障碍技巧决赛中，中国选手谷爱凌夺得银牌。祝贺谷爱凌！今天上午，自由式滑雪女子坡面障碍技巧决赛举行。决赛分三轮进行，取选手最佳成绩排名决出奖牌。第一跳，中国选手谷爱凌获得69.90分。在12位选手中排名第三。完成动作后，谷爱凌又扮了个鬼脸，甚是可爱。第二轮中，谷爱凌在道具区第三个障碍处失误，落地时摔倒。获得16.98分。网友：摔倒了也没关系，继续加油！在第二跳失误摔倒的情况下，谷爱凌顶住压力，第三跳稳稳发挥，流畅落地！获得86.23分！此轮比赛，共12位选手参赛，谷爱凌第10位出场。网友：看比赛时我比谷爱凌紧张，加油！"
+text = ""
 inputs = tokenizer(text, max_length=1024, return_tensors="pt")
 
 # Generate Summary