Upload 22 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sbert/models--shibing624--text2vec-base-chinese/blobs/0c855515479137398ce4ea985628548d4e8ed8c5764656dac966d6a24f39e721 filter=lfs diff=lfs merge=lfs -text

sbert/models--shibing624--text2vec-base-chinese/blobs/0c855515479137398ce4ea985628548d4e8ed8c5764656dac966d6a24f39e721

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c855515479137398ce4ea985628548d4e8ed8c5764656dac966d6a24f39e721
+size 409098104

sbert/models--shibing624--text2vec-base-chinese/blobs/2c787222b8b9fc64a5a5c6bcf7506e2c4906bec5

@@ -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"
+  }
+]

sbert/models--shibing624--text2vec-base-chinese/blobs/5bdf2723485c9b6e797c26b1c59edf10a638051d

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "hfl/chinese-macbert-base", "tokenizer_class": "BertTokenizer"}

sbert/models--shibing624--text2vec-base-chinese/blobs/6cf65ba8116d461a2baa0039d80bbc4b3eb7600b

@@ -0,0 +1,4 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_mean_tokens": true
+}

sbert/models--shibing624--text2vec-base-chinese/blobs/7fac338dfa876bf83d235a13e72b06b21ea4f552

@@ -0,0 +1,238 @@
+---
+license: apache-2.0
+pipeline_tag: sentence-similarity
+tags:
+- Sentence Transformers
+- sentence-similarity
+- sentence-transformers
+datasets:
+- shibing624/nli_zh
+language:
+- zh
+library_name: sentence-transformers
+---
+
+
+# shibing624/text2vec-base-chinese
+This is a CoSENT(Cosine Sentence) model: shibing624/text2vec-base-chinese.
+
+It maps sentences to a 768 dimensional dense vector space and can be used for tasks 
+like sentence embeddings, text matching or semantic search.
+
+
+## Evaluation
+For an automated evaluation of this model, see the *Evaluation Benchmark*: [text2vec](https://github.com/shibing624/text2vec)
+
+- chinese text matching task：
+
+| Arch       | BaseModel                         | Model                                                                                                                                             | ATEC  |  BQ   | LCQMC | PAWSX | STS-B | SOHU-dd | SOHU-dc |    Avg    |  QPS  |
+|:-----------|:----------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------|:-----:|:-----:|:-----:|:-----:|:-----:|:-------:|:-------:|:---------:|:-----:|
+| Word2Vec   | word2vec                          | [w2v-light-tencent-chinese](https://ai.tencent.com/ailab/nlp/en/download.html)                                                                    | 20.00 | 31.49 | 59.46 | 2.57  | 55.78 |  55.04  |  20.70  |   35.03   | 23769 |
+| SBERT      | xlm-roberta-base                  | [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) | 18.42 | 38.52 | 63.96 | 10.14 | 78.90 |  63.01  |  52.28  |   46.46   | 3138  |
+| Instructor | hfl/chinese-roberta-wwm-ext       | [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base)                                                                                       | 41.27 | 63.81 | 74.87 | 12.20 | 76.96 |  75.83  |  60.55  |   57.93   | 2980  |
+| CoSENT     | hfl/chinese-macbert-base          | [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese)                                                       | 31.93 | 42.67 | 70.16 | 17.21 | 79.30 |  70.27  |  50.42  |   51.61   | 3008  |
+| CoSENT     | hfl/chinese-lert-large            | [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese)                                                   | 32.61 | 44.59 | 69.30 | 14.51 | 79.44 |  73.01  |  59.04  |   53.12   | 2092  |
+| CoSENT     | nghuyong/ernie-3.0-base-zh        | [shibing624/text2vec-base-chinese-sentence](https://huggingface.co/shibing624/text2vec-base-chinese-sentence)                                     | 43.37 | 61.43 | 73.48 | 38.90 | 78.25 |  70.60  |  53.08  |   59.87   | 3089  |
+| CoSENT     | nghuyong/ernie-3.0-base-zh        | [shibing624/text2vec-base-chinese-paraphrase](https://huggingface.co/shibing624/text2vec-base-chinese-paraphrase)                                 | 44.89 | 63.58 | 74.24 | 40.90 | 78.93 |  76.70  |  63.30  |    63.08  | 3066  |
+| CoSENT     | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2  | [shibing624/text2vec-base-multilingual](https://huggingface.co/shibing624/text2vec-base-multilingual)                                             | 32.39 | 50.33 | 65.64 | 32.56 | 74.45 |  68.88  |  51.17  |   53.67   | 4004  |
+
+
+说明：
+- 结果评测指标：spearman系数
+- `shibing624/text2vec-base-chinese`模型，是用CoSENT方法训练，基于`hfl/chinese-macbert-base`在中文STS-B数据训练得到，并在中文STS-B测试集评估达到较好效果，运行[examples/training_sup_text_matching_model.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model.py)代码可训练模型，模型文件已经上传HF model hub，中文通用语义匹配任务推荐使用
+- `shibing624/text2vec-base-chinese-sentence`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集[shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-sentence-dataset)训练得到，并在中文各NLI测试集评估达到较好效果，运行[examples/training_sup_text_matching_model_jsonl_data.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model_jsonl_data.py)代码可训练模型，模型文件已经上传HF model hub，中文s2s(句子vs句子)语义匹配任务推荐使用
+- `shibing624/text2vec-base-chinese-paraphrase`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集[shibing624/nli-zh-all/text2vec-base-chinese-paraphrase-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-paraphrase-dataset)，数据集相对于[shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-sentence-dataset)加入了s2p(sentence to paraphrase)数据，强化了其长文本的表征能力，并在中文各NLI测试集评估达到SOTA，运行[examples/training_sup_text_matching_model_jsonl_data.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model_jsonl_data.py)代码可训练模型，模型文件已经上传HF model hub，中文s2p(句子vs段落)语义匹配任务推荐使用
+- `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`模型是用SBERT训练，是`paraphrase-MiniLM-L12-v2`模型的多语言版本，支持中文、英文等
+- `w2v-light-tencent-chinese`是腾讯词向量的Word2Vec模型，CPU加载使用，适用于中文字面匹配任务和缺少数据的冷启动情况
+
+## Usage (text2vec)
+Using this model becomes easy when you have [text2vec](https://github.com/shibing624/text2vec) installed:
+
+```
+pip install -U text2vec
+```
+
+Then you can use the model like this:
+
+```python
+from text2vec import SentenceModel
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+
+model = SentenceModel('shibing624/text2vec-base-chinese')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Usage (HuggingFace Transformers)
+Without [text2vec](https://github.com/shibing624/text2vec), you can use the model like this: 
+
+First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+Install transformers:
+```
+pip install transformers
+```
+
+Then load model and predict:
+```python
+from transformers import BertTokenizer, BertModel
+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)
+
+# Load model from HuggingFace Hub
+tokenizer = BertTokenizer.from_pretrained('shibing624/text2vec-base-chinese')
+model = BertModel.from_pretrained('shibing624/text2vec-base-chinese')
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+# 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)
+```
+
+## Usage (sentence-transformers)
+[sentence-transformers](https://github.com/UKPLab/sentence-transformers) is a popular library to compute dense vector representations for sentences.
+
+Install sentence-transformers:
+```
+pip install -U sentence-transformers
+```
+
+Then load model and predict:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+m = SentenceTransformer("shibing624/text2vec-base-chinese")
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+
+sentence_embeddings = m.encode(sentences)
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+## Model speed up
+
+
+| Model                                                                                                                        | ATEC              | BQ                | LCQMC            | PAWSX            | STSB             |
+|------------------------------------------------------------------------------------------------------------------------------|-------------------|-------------------|------------------|------------------|------------------|
+| shibing624/text2vec-base-chinese (fp32, baseline)                                                                            | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (onnx-O4, [#29](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/29))    | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (ov, [#27](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/27))         | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (ov-qint8, [#30](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/30))   | 0.30778 (-3.60%)  | 0.43474 (+1.88%)  | 0.69620 (-0.77%) | 0.16662 (-3.20%) | 0.79396 (+0.13%) |
+
+In short:
+1. ✅ shibing624/text2vec-base-chinese (onnx-O4), ONNX Optimized to [O4](https://huggingface.co/docs/optimum/en/onnxruntime/usage_guides/optimization) does not reduce performance, but gives a [~2x speedup](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#benchmarks) on GPU.
+2. ✅ shibing624/text2vec-base-chinese (ov), OpenVINO does not reduce performance, but gives a 1.12x speedup on CPU.
+3. 🟡 shibing624/text2vec-base-chinese (ov-qint8), int8 quantization with OV incurs a small performance hit on some tasks, and a tiny performance gain on others, when quantizing with [Chinese STSB](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt). Additionally, it results in a [4.78x speedup](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#benchmarks) on CPU.
+
+- usage: shibing624/text2vec-base-chinese (onnx-O4), for gpu
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="onnx",
+    model_kwargs={"file_name": "model_O4.onnx"},
+)
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+
+- usage: shibing624/text2vec-base-chinese (ov), for cpu
+```python
+# pip install 'optimum[openvino]'
+
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="openvino",
+)
+
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+- usage: shibing624/text2vec-base-chinese (ov-qint8), for cpu
+```python
+# pip install optimum
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="onnx",
+    model_kwargs={"file_name": "model_qint8_avx512_vnni.onnx"},
+)
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+
+## Full Model Architecture
+```
+CoSENT(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_mean_tokens': True})
+)
+```
+
+## Intended uses
+
+Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures 
+the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
+
+By default, input text longer than 256 word pieces is truncated.
+
+
+## Training procedure
+
+### Pre-training 
+
+We use the pretrained [`hfl/chinese-macbert-base`](https://huggingface.co/hfl/chinese-macbert-base) model. 
+Please refer to the model card for more detailed information about the pre-training procedure.
+
+### Fine-tuning 
+
+We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each 
+possible sentence pairs from the batch.
+We then apply the rank loss by comparing with true pairs and false pairs.
+
+#### Hyper parameters
+
+- training dataset: https://huggingface.co/datasets/shibing624/nli_zh
+- max_seq_length: 128
+- best epoch: 5
+- sentence embedding dim: 768
+
+
+
+## Citing & Authors
+This model was trained by [text2vec](https://github.com/shibing624/text2vec). 
+        
+If you find this model helpful, feel free to cite:
+```bibtex 
+@software{text2vec,
+  author = {Xu Ming},
+  title = {text2vec: A Tool for Text to Vector},
+  year = {2022},
+  url = {https://github.com/shibing624/text2vec},
+}
+```

sbert/models--shibing624--text2vec-base-chinese/blobs/90e03d46bdb660cb7a95fb0200a35e456457f78c

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "hfl/chinese-macbert-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "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": "4.12.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

sbert/models--shibing624--text2vec-base-chinese/blobs/e0021d480d68dfdf363d3639ee7f3c00f63239f7

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sbert/models--shibing624--text2vec-base-chinese/blobs/e7b0375001f109a6b8873d756ad4f7bbb15fbaa5

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

sbert/models--shibing624--text2vec-base-chinese/refs/main

@@ -0,0 +1 @@
+183bb99aa7af74355fb58d16edf8c13ae7c5433e

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/1_Pooling/config.json

@@ -0,0 +1,4 @@
+{
+  "word_embedding_dimension": 768,
+  "pooling_mode_mean_tokens": true
+}

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/README.md

@@ -0,0 +1,238 @@
+---
+license: apache-2.0
+pipeline_tag: sentence-similarity
+tags:
+- Sentence Transformers
+- sentence-similarity
+- sentence-transformers
+datasets:
+- shibing624/nli_zh
+language:
+- zh
+library_name: sentence-transformers
+---
+
+
+# shibing624/text2vec-base-chinese
+This is a CoSENT(Cosine Sentence) model: shibing624/text2vec-base-chinese.
+
+It maps sentences to a 768 dimensional dense vector space and can be used for tasks 
+like sentence embeddings, text matching or semantic search.
+
+
+## Evaluation
+For an automated evaluation of this model, see the *Evaluation Benchmark*: [text2vec](https://github.com/shibing624/text2vec)
+
+- chinese text matching task：
+
+| Arch       | BaseModel                         | Model                                                                                                                                             | ATEC  |  BQ   | LCQMC | PAWSX | STS-B | SOHU-dd | SOHU-dc |    Avg    |  QPS  |
+|:-----------|:----------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------|:-----:|:-----:|:-----:|:-----:|:-----:|:-------:|:-------:|:---------:|:-----:|
+| Word2Vec   | word2vec                          | [w2v-light-tencent-chinese](https://ai.tencent.com/ailab/nlp/en/download.html)                                                                    | 20.00 | 31.49 | 59.46 | 2.57  | 55.78 |  55.04  |  20.70  |   35.03   | 23769 |
+| SBERT      | xlm-roberta-base                  | [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) | 18.42 | 38.52 | 63.96 | 10.14 | 78.90 |  63.01  |  52.28  |   46.46   | 3138  |
+| Instructor | hfl/chinese-roberta-wwm-ext       | [moka-ai/m3e-base](https://huggingface.co/moka-ai/m3e-base)                                                                                       | 41.27 | 63.81 | 74.87 | 12.20 | 76.96 |  75.83  |  60.55  |   57.93   | 2980  |
+| CoSENT     | hfl/chinese-macbert-base          | [shibing624/text2vec-base-chinese](https://huggingface.co/shibing624/text2vec-base-chinese)                                                       | 31.93 | 42.67 | 70.16 | 17.21 | 79.30 |  70.27  |  50.42  |   51.61   | 3008  |
+| CoSENT     | hfl/chinese-lert-large            | [GanymedeNil/text2vec-large-chinese](https://huggingface.co/GanymedeNil/text2vec-large-chinese)                                                   | 32.61 | 44.59 | 69.30 | 14.51 | 79.44 |  73.01  |  59.04  |   53.12   | 2092  |
+| CoSENT     | nghuyong/ernie-3.0-base-zh        | [shibing624/text2vec-base-chinese-sentence](https://huggingface.co/shibing624/text2vec-base-chinese-sentence)                                     | 43.37 | 61.43 | 73.48 | 38.90 | 78.25 |  70.60  |  53.08  |   59.87   | 3089  |
+| CoSENT     | nghuyong/ernie-3.0-base-zh        | [shibing624/text2vec-base-chinese-paraphrase](https://huggingface.co/shibing624/text2vec-base-chinese-paraphrase)                                 | 44.89 | 63.58 | 74.24 | 40.90 | 78.93 |  76.70  |  63.30  |    63.08  | 3066  |
+| CoSENT     | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2  | [shibing624/text2vec-base-multilingual](https://huggingface.co/shibing624/text2vec-base-multilingual)                                             | 32.39 | 50.33 | 65.64 | 32.56 | 74.45 |  68.88  |  51.17  |   53.67   | 4004  |
+
+
+说明：
+- 结果评测指标：spearman系数
+- `shibing624/text2vec-base-chinese`模型，是用CoSENT方法训练，基于`hfl/chinese-macbert-base`在中文STS-B数据训练得到，并在中文STS-B测试集评估达到较好效果，运行[examples/training_sup_text_matching_model.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model.py)代码可训练模型，模型文件已经上传HF model hub，中文通用语义匹配任务推荐使用
+- `shibing624/text2vec-base-chinese-sentence`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集[shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-sentence-dataset)训练得到，并在中文各NLI测试集评估达到较好效果，运行[examples/training_sup_text_matching_model_jsonl_data.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model_jsonl_data.py)代码可训练模型，模型文件已经上传HF model hub，中文s2s(句子vs句子)语义匹配任务推荐使用
+- `shibing624/text2vec-base-chinese-paraphrase`模型，是用CoSENT方法训练，基于`nghuyong/ernie-3.0-base-zh`用人工挑选后的中文STS数据集[shibing624/nli-zh-all/text2vec-base-chinese-paraphrase-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-paraphrase-dataset)，数据集相对于[shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset](https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-sentence-dataset)加入了s2p(sentence to paraphrase)数据，强化了其长文本的表征能力，并在中文各NLI测试集评估达到SOTA，运行[examples/training_sup_text_matching_model_jsonl_data.py](https://github.com/shibing624/text2vec/blob/master/examples/training_sup_text_matching_model_jsonl_data.py)代码可训练模型，模型文件已经上传HF model hub，中文s2p(句子vs段落)语义匹配任务推荐使用
+- `sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2`模型是用SBERT训练，是`paraphrase-MiniLM-L12-v2`模型的多语言版本，支持中文、英文等
+- `w2v-light-tencent-chinese`是腾讯词向量的Word2Vec模型，CPU加载使用，适用于中文字面匹配任务和缺少数据的冷启动情况
+
+## Usage (text2vec)
+Using this model becomes easy when you have [text2vec](https://github.com/shibing624/text2vec) installed:
+
+```
+pip install -U text2vec
+```
+
+Then you can use the model like this:
+
+```python
+from text2vec import SentenceModel
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+
+model = SentenceModel('shibing624/text2vec-base-chinese')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+## Usage (HuggingFace Transformers)
+Without [text2vec](https://github.com/shibing624/text2vec), you can use the model like this: 
+
+First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+Install transformers:
+```
+pip install transformers
+```
+
+Then load model and predict:
+```python
+from transformers import BertTokenizer, BertModel
+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)
+
+# Load model from HuggingFace Hub
+tokenizer = BertTokenizer.from_pretrained('shibing624/text2vec-base-chinese')
+model = BertModel.from_pretrained('shibing624/text2vec-base-chinese')
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+# 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)
+```
+
+## Usage (sentence-transformers)
+[sentence-transformers](https://github.com/UKPLab/sentence-transformers) is a popular library to compute dense vector representations for sentences.
+
+Install sentence-transformers:
+```
+pip install -U sentence-transformers
+```
+
+Then load model and predict:
+
+```python
+from sentence_transformers import SentenceTransformer
+
+m = SentenceTransformer("shibing624/text2vec-base-chinese")
+sentences = ['如何更换花呗绑定银行卡', '花呗更改绑定银行卡']
+
+sentence_embeddings = m.encode(sentences)
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+## Model speed up
+
+
+| Model                                                                                                                        | ATEC              | BQ                | LCQMC            | PAWSX            | STSB             |
+|------------------------------------------------------------------------------------------------------------------------------|-------------------|-------------------|------------------|------------------|------------------|
+| shibing624/text2vec-base-chinese (fp32, baseline)                                                                            | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (onnx-O4, [#29](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/29))    | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (ov, [#27](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/27))         | 0.31928           | 0.42672           | 0.70157          | 0.17214          | 0.79296          |
+| shibing624/text2vec-base-chinese (ov-qint8, [#30](https://huggingface.co/shibing624/text2vec-base-chinese/discussions/30))   | 0.30778 (-3.60%)  | 0.43474 (+1.88%)  | 0.69620 (-0.77%) | 0.16662 (-3.20%) | 0.79396 (+0.13%) |
+
+In short:
+1. ✅ shibing624/text2vec-base-chinese (onnx-O4), ONNX Optimized to [O4](https://huggingface.co/docs/optimum/en/onnxruntime/usage_guides/optimization) does not reduce performance, but gives a [~2x speedup](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#benchmarks) on GPU.
+2. ✅ shibing624/text2vec-base-chinese (ov), OpenVINO does not reduce performance, but gives a 1.12x speedup on CPU.
+3. 🟡 shibing624/text2vec-base-chinese (ov-qint8), int8 quantization with OV incurs a small performance hit on some tasks, and a tiny performance gain on others, when quantizing with [Chinese STSB](https://huggingface.co/datasets/PhilipMay/stsb_multi_mt). Additionally, it results in a [4.78x speedup](https://sbert.net/docs/sentence_transformer/usage/efficiency.html#benchmarks) on CPU.
+
+- usage: shibing624/text2vec-base-chinese (onnx-O4), for gpu
+```python
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="onnx",
+    model_kwargs={"file_name": "model_O4.onnx"},
+)
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+
+- usage: shibing624/text2vec-base-chinese (ov), for cpu
+```python
+# pip install 'optimum[openvino]'
+
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="openvino",
+)
+
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+- usage: shibing624/text2vec-base-chinese (ov-qint8), for cpu
+```python
+# pip install optimum
+from sentence_transformers import SentenceTransformer
+
+model = SentenceTransformer(
+    "shibing624/text2vec-base-chinese",
+    backend="onnx",
+    model_kwargs={"file_name": "model_qint8_avx512_vnni.onnx"},
+)
+embeddings = model.encode(["如何更换花呗绑定银行卡", "花呗更改绑定银行卡", "你是谁"])
+print(embeddings.shape)
+similarities = model.similarity(embeddings, embeddings)
+print(similarities)
+```
+
+
+## Full Model Architecture
+```
+CoSENT(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_mean_tokens': True})
+)
+```
+
+## Intended uses
+
+Our model is intented to be used as a sentence and short paragraph encoder. Given an input text, it ouptuts a vector which captures 
+the semantic information. The sentence vector may be used for information retrieval, clustering or sentence similarity tasks.
+
+By default, input text longer than 256 word pieces is truncated.
+
+
+## Training procedure
+
+### Pre-training 
+
+We use the pretrained [`hfl/chinese-macbert-base`](https://huggingface.co/hfl/chinese-macbert-base) model. 
+Please refer to the model card for more detailed information about the pre-training procedure.
+
+### Fine-tuning 
+
+We fine-tune the model using a contrastive objective. Formally, we compute the cosine similarity from each 
+possible sentence pairs from the batch.
+We then apply the rank loss by comparing with true pairs and false pairs.
+
+#### Hyper parameters
+
+- training dataset: https://huggingface.co/datasets/shibing624/nli_zh
+- max_seq_length: 128
+- best epoch: 5
+- sentence embedding dim: 768
+
+
+
+## Citing & Authors
+This model was trained by [text2vec](https://github.com/shibing624/text2vec). 
+        
+If you find this model helpful, feel free to cite:
+```bibtex 
+@software{text2vec,
+  author = {Xu Ming},
+  title = {text2vec: A Tool for Text to Vector},
+  year = {2022},
+  url = {https://github.com/shibing624/text2vec},
+}
+```

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "hfl/chinese-macbert-base",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "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": "4.12.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c855515479137398ce4ea985628548d4e8ed8c5764656dac966d6a24f39e721
+size 409098104

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/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"
+  }
+]

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/special_tokens_map.json

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

sbert/models--shibing624--text2vec-base-chinese/snapshots/183bb99aa7af74355fb58d16edf8c13ae7c5433e/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "name_or_path": "hfl/chinese-macbert-base", "tokenizer_class": "BertTokenizer"}