Update README.md

README.md

@@ -1,91 +1,37 @@
----
-pipeline_tag: sentence-similarity
-tags:
-- sentence-transformers
-- feature-extraction
-- sentence-similarity
+## acgvoc2vec
 
----
+结构为[sentence-transformers](https://github.com/UKPLab/sentence-transformers)，使用其**distiluse-base-multilingual-cased-v2**预训练权重，以5e-5的学习率在动漫相关语句对数据集下进行微调，损失函数为MultipleNegativesRankingLoss。
 
-# {MODEL_NAME}
+数据集主要包括：
 
-This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 512 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+* Bangumi
 
-<!--- Describe your model here -->
+  * 动画日文名-动画中文名
+  * 动画日文名-简介
+  * 动画中文名-简介
+  * 动画中文名-标签
+  * 动画日文名-角色
+  * 动画中文名-角色
+  * 声优日文名-声优中文名
 
-## Usage (Sentence-Transformers)
+* pixiv
 
-Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+  * 标签日文名-标签中文名
+* AnimeList
 
-```
-pip install -U sentence-transformers
-```
+  * 动画日文名-动画英文名
 
-Then you can use the model like this:
+* 维基百科
 
-```python
-from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+  * 动画日文名-动画中文名
+  * 动画日文名-动画英文名
+  * 中英日详情页h2标题及其对应文本
+  * 简介多语言对照（中日英）
+  * 动画名-简介（中日英）  
 
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
-```
+* moegirl
 
+  * 动画中文名的简介-简介
+* 动画中文名+小标题-对应内容
 
-
-## Evaluation Results
-
-<!--- Describe how your model was evaluated -->
-
-For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
-
-
-## Training
-The model was trained with the parameters:
-
-**DataLoader**:
-
-`torch.utils.data.dataloader.DataLoader` of length 64769 with parameters:
-```
-{'batch_size': 80, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
-```
-
-**Loss**:
-
-`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
-  ```
-  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
-  ```
-
-Parameters of the fit()-Method:
-```
-{
-    "epochs": 20,
-    "evaluation_steps": 0,
-    "evaluator": "NoneType",
-    "max_grad_norm": 1,
-    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
-    "optimizer_params": {
-        "lr": 2e-05
-    },
-    "scheduler": "WarmupLinear",
-    "steps_per_epoch": null,
-    "warmup_steps": 129538,
-    "weight_decay": 0.01
-}
-```
-
-
-## Full Model Architecture
-```
-SentenceTransformer(
-  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel 
-  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
-  (2): Dense({'in_features': 768, 'out_features': 512, 'bias': True, 'activation_function': 'torch.nn.modules.activation.Tanh'})
-)
-```
-
-## Citing & Authors
-
-<!--- Describe where people can find more information -->
+在进行爬取，清洗，处理后得到510w对文本对（还在持续增加），batchzise=80训练了20个epoch，使st的权重能够适应该问题空间，生成融合了领域知识的文本特征向量（体现为有关的文本距离更加接近，例如作品与登场人物，或者来自同一作品的登场人物）。