First commit

README.md

@@ -1,3 +1,117 @@
 ---
+language:
+  - zh
 license: apache-2.0
+# inference: false
+
+# inference:
+#   parameters:
+tags:
+  - question-generation
+  - qg
+  - SQuAD
+  - nlg
+  - bart-base
+datasets:
+  - chinesesquad
+metrics:
+  - bleu
+  - rouge
+  - f1
+  - meteor
+  - bleu_score
 ---
+
+# Randeng-BART-139M-QG-Chinese
+
+- Github: [Fengshenbang-LM](https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/dev_yangqi/fengshen/examples/bart_qg)
+- Docs: [Fengshenbang-Docs](https://fengshenbang-doc.readthedocs.io/)
+
+## 简介 Brief Introduction
+
+善于处理问题生成任务的中文版 BART-base 模型。
+
+Good at solving question generation tasks Bart-base Model (Chinese version).
+
+## 模型分类 Model Taxonomy
+
+|  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 | BART |      139M      |    问题生成任务-中文 QuestionGeneration-Chinese    |
+
+
+## 模型信息 Model Information
+
+基于[IDEA-CCNL/Randeng-BART-139M](https://huggingface.co/IDEA-CCNL/Randeng-BART-139M)，我们在 [ChineseSQuAD](https://github.com/pluto-junzeng/ChineseSquad) 数据集上微调了问题生成任务版本。该数据集翻译了部分SQuAD数据集，包含约 67k 有答案的训练样本。
+
+Based on [IDEA-CCNL/Randeng-BART-139M](https://huggingface.co/IDEA-CCNL/Randeng-BART-139M), we fine-tuned a question generation version on [ChineseSQuAD](https://github.com/pluto-junzeng/ChineseSquad) datasets. The dataset is translated from SQuAD 2.0, with around 67k samples with answer.
+
+### 下游效果 Performance
+| Dataset          |  Size  | BLEU-4 | METEOR | ROUGE-L| 
+| ------------ | -----  | -------- |--------- | ---------- |
+|   ChineseSQuAD               |  139M   |  22.17 |   40.38  |   38.17   | 
+
+## 使用 Usage
+
+```python
+from transformers import AutoTokenizer, BartForConditionalGeneration
+tokenizer = AutoTokenizer.from_pretrained("IDEA-CCNL/Randeng-BART-139M-QG-Chinese",additional_special_tokens=["<ans>"])
+model = BartForConditionalGeneration.from_pretrained("IDEA-CCNL/Randeng-BART-139M-QG-Chinese")
+
+context = "知识：1939年9月1日德国入侵波兰后，第二次世界大战开始，华沙一直被保卫到9月27日。波兰中部，包括华沙，都在德国纳粹殖民地政府总政府的统治下。所有的高等教育机构都立即关闭，华沙的犹太人口——几十万，约占城市的 <ans> ——全部涌入华沙的贫民区。回答：30%"
+inputs = tokenizer.encode_plus(
+            context,
+            max_length=448,
+            padding="max_length",
+            truncation=True,
+            return_tensors='pt'
+        )
+out = model.generate(                
+        input_ids=inputs['input_ids'],
+        attention_mask=inputs['attention_mask'],
+        do_sample=True,
+        num_beams=5,
+        max_length=64,
+        top_p = 0.9,
+    )
+print(pred = tokenizer.batch_decode(out,clean_up_tokenization_spaces=True, skip_special_tokens=True)[0])
+# 问题:华沙的犹太人口占城市的百分之多少?
+```
+
+
+## 引用 Citation
+
+如果您在您的工作中使用了我们的模型，可以引用我们的[论文](https://arxiv.org/abs/2210.08590)：
+
+If you are using the resource for your work, please cite the our [paper](https://arxiv.org/abs/2210.08590):
+
+```text
+@article{unimc,
+  author    = {Ping Yang and
+               Junjie Wang and
+               Ruyi Gan and
+               Xinyu Zhu and
+               Lin Zhang and
+               Ziwei Wu and
+               Xinyu Gao and
+               Jiaxing Zhang and
+               Tetsuya Sakai},
+  title     = {Zero-Shot Learners for Natural Language Understanding via a Unified Multiple Choice Perspective},
+  journal   = {CoRR},
+  volume    = {abs/2210.08590},
+  year      = {2022}
+}
+```
+
+也可以引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
+
+You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
+
+```text
+@misc{Fengshenbang-LM,
+  title={Fengshenbang-LM},
+  author={IDEA-CCNL},
+  year={2021},
+  howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
+}
+```

added_tokens.json

@@ -0,0 +1 @@
+{"<mask>": 40001, "<pad>": 40000}

config.json

@@ -0,0 +1,52 @@
+{
+  "_name_or_path": "/cognitive_comp/yangqi/model/Randeng-BART-139M/",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.19.2",
+  "use_cache": true,
+  "vocab_size": 40005
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "additional_special_tokens": ["<s>", "<mask>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1836aa16c5e41fb9bec14c477218b83812919d19dfdde1c49a419cd9935615
+size 858518

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+    "eos_token": "</s>",
+    "unk_token": "<unk>",
+    "pad_token": "<pad>",
+    "extra_ids": 0,
+    "additional_special_tokens": [
+        "<s>",
+        "<mask>"
+    ],
+    "sp_model_kwargs": {},
+    "name_or_path": "/cognitive_comp/gaoxinyu/hf_hub/Randeng-BART-139M",
+    "special_tokens_map_file": "/cognitive_comp/gaoxinyu/hf_hub/Randeng-BART-139M/special_tokens_map.json",
+    "tokenizer_class": "T5Tokenizer"
+}