Create README.md

README.md

@@ -0,0 +1,90 @@
+---
+language: zh
+tags:
+- summarization
+inference: False
+---
+
+
+Randeng_Pegasus_523M_Summary model (Chinese)，which codes has merged into [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM)
+
+The 523M million parameter randeng_pegasus_large model, training with sampled gap sentence ratios on 180G Chinese data, and stochastically sample important sentences. The pretraining task just same as the paper [PEGASUS: Pre-training with Extracted Gap-sentences for
+Abstractive Summarization](https://arxiv.org/pdf/1912.08777.pdf) mentioned.
+
+Different from the English version of pegasus, considering that the Chinese sentence piece is unstable, we use jieba and Bertokenizer as the tokenizer in chinese pegasus model.
+
+This model we provided in hugging face hub is only the pretrained model, has not finetuned with download data yet.
+
+We also pretained a base model, available with [Randeng_Pegasus_238M_Summary](https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_238M_Summary)
+
+
+Task: Summarization
+
+## Usage
+```python
+from transformers import PegasusForConditionalGeneration
+import jieba
+jieba.initialize()
+# Need to download tokenizers_pegasus.py and other Python script from Fengshenbang-LM github repo in advance,
+# or you can mv download in tokenizers_pegasus.py and data_utils.py in https://huggingface.co/IDEA-CCNL/Randeng_Pegasus_523M_Summary/tree/main
+# 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/pegasus/
+# and then you will see the tokenizers_pegasus.py and data_utils.py which are needed by pegasus model
+# from tokenizers_pegasus import PegasusTokenizer
+class PegasusTokenizer(BertTokenizer):
+    model_input_names = ["input_ids", "attention_mask"]
+    def __init__(self, pre_tokenizer=lambda x: jieba.cut(x, HMM=False), **kwargs):
+        self.pre_tokenizer = pre_tokenizer
+        super().__init__(pre_tokenizer=self.pre_tokenizer, **kwargs)
+        self.add_special_tokens({'additional_special_tokens':["<mask_1>"]})
+
+    def build_inputs_with_special_tokens(
+            self,
+            token_ids_0: List[int],
+            token_ids_1: Optional[List[int]] = None) -> List[int]:
+
+        if token_ids_1 is None:
+            return token_ids_0 + [self.eos_token_id]
+        return token_ids_0 + token_ids_1 + [self.eos_token_id]
+
+    def _special_token_mask(self, seq):
+        all_special_ids = set(
+            self.all_special_ids)  # call it once instead of inside list comp
+        # all_special_ids.remove(self.unk_token_id)  # <unk> is only sometimes special
+        return [1 if x in all_special_ids else 0 for x in seq]
+
+    def get_special_tokens_mask(
+            self,
+            token_ids_0: List[int],
+            token_ids_1: Optional[List[int]] = None,
+            already_has_special_tokens: bool = False) -> List[int]:
+        if already_has_special_tokens:
+            return self._special_token_mask(token_ids_0)
+        elif token_ids_1 is None:
+            return self._special_token_mask(token_ids_0) + [self.eos_token_id]
+        else:
+            return self._special_token_mask(token_ids_0 +
+                                            token_ids_1) + [self.eos_token_id]
+                                            
+model = PegasusForConditionalGeneration.from_pretrained("IDEA-CCNL/randeng_pegasus_523M_summary")
+tokenizer = PegasusTokenizer.from_pretrained("path/to/vocab.txt")
+
+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！"
+inputs = tokenizer(text, max_length=1024, return_tensors="pt")
+
+# Generate Summary
+summary_ids = model.generate(inputs["input_ids"])
+tokenizer.batch_decode(summary_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
+```
+
+## Citation
+If you find the resource is useful, please cite the following website in your paper.
+```
+@misc{Fengshenbang-LM,
+  title={Fengshenbang-LM},
+  author={IDEA-CCNL},
+  year={2022},
+  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
+}
+```