Add SetFit model

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "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
+}

README.md

@@ -0,0 +1,89 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- semantic-search
+- chinese
+---
+
+# DMetaSoul/sbert-chinese-general-v2
+
+此模型基于 [bert-base-chinese](https://huggingface.co/bert-base-chinese) 版本 BERT 模型，在百万级语义相似数据集 [SimCLUE](https://github.com/CLUEbenchmark/SimCLUE) 上进行训练，适用于**通用语义匹配**场景，从效果来看该模型在各种任务上**泛化能力更好**。
+
+注：此模型的[轻量化版本](https://huggingface.co/DMetaSoul/sbert-chinese-general-v2-distill)，也已经开源啦！
+
+# Usage
+
+## 1. Sentence-Transformers
+
+通过  [sentence-transformers](https://www.SBERT.net) 框架来使用该模型，首先进行安装：
+
+```
+pip install -U sentence-transformers
+```
+
+然后使用下面的代码来载入该模型并进行文本表征向量的提取：
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["我的儿子！他猛然间喊道，我的儿子在哪儿？", "我的儿子呢！他突然喊道，我的儿子在哪里？"]
+
+model = SentenceTransformer('DMetaSoul/sbert-chinese-general-v2')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## 2. HuggingFace Transformers
+
+如果不想使用   [sentence-transformers](https://www.SBERT.net) 的话，也可以通过 HuggingFace Transformers 来载入该模型并进行文本向量抽取：
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ["我的儿子！他猛然间喊道，我的儿子在哪儿？", "我的儿子呢！他突然喊道，我的儿子在哪里？"]
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('DMetaSoul/sbert-chinese-general-v2')
+model = AutoModel.from_pretrained('DMetaSoul/sbert-chinese-general-v2')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+## Evaluation
+
+该模型在公开的几个语义匹配数据集上进行了评测，计算了向量相似度跟真实标签之间的相关性系数：
+
+|                              | **csts_dev** | **csts_test** | **afqmc**  | **lcqmc**  | **bqcorpus** | **pawsx**  | **xiaobu** |
+| ---------------------------- | ------------ | ------------- | ---------- | ---------- | ------------ | ---------- | ---------- |
+| **sbert-chinese-general-v1** | **84.54%**   | **82.17%**    | 23.80%     | 65.94%     | 45.52%       | 11.52%     | 48.51%     |
+| **sbert-chinese-general-v2** | 77.20%       | 72.60%        | **36.80%** | **76.92%** | **49.63%**   | **16.24%** | **63.16%** |
+
+这里对比了本模型跟之前我们发布 [sbert-chinese-general-v1](https://huggingface.co/DMetaSoul/sbert-chinese-general-v1) 之间的差异，可以看到本模型在多个任务上的泛化能力更好。
+
+## Citing & Authors
+
+E-mail: xiaowenbin@dmetasoul.com

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "/home/taohe/.cache/torch/sentence_transformers/DMetaSoul_sbert-chinese-general-v2/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.22.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.1.0",
+    "transformers": "4.16.0",
+    "pytorch": "1.10.2"
+  }
+}

model_head.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295e6ff83ee8d3109f85127d6fafc14883f6ca76a1c78115508afd2329f21a50
+size 394

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3038f0a407cc45b3fa5685e47540b7f5a833e741ddf7e915017f96b8405f7d
+size 409138989

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 256,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "/home/taohe/.cache/torch/sentence_transformers/DMetaSoul_sbert-chinese-general-v2/",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}