shibing624/text2vec-bge-large-chinese

This is a CoSENT(Cosine Sentence) model: shibing624/text2vec-bge-large-chinese.

It maps sentences to a 1024 dimensional dense vector space and can be used for tasks like sentence embeddings, text matching or semantic search.

• training dataset: https://huggingface.co/datasets/shibing624/nli-zh-all/tree/main/text2vec-base-chinese-paraphrase-dataset
• base model: https://huggingface.co/BAAI/bge-large-zh-noinstruct
• max_seq_length: 256
• best epoch: 4
• sentence embedding dim: 1024

Evaluation

For an automated evaluation of this model, see the Evaluation Benchmark: text2vec

Release Models

• 本项目release模型的中文匹配评测结果：

Arch	BaseModel	Model	ATEC	BQ	LCQMC	PAWSX	STS-B	SOHU-dd	SOHU-dc	Avg	QPS
Word2Vec	word2vec	w2v-light-tencent-chinese	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	18.42	38.52	63.96	10.14	78.90	63.01	52.28	46.46	3138
CoSENT	hfl/chinese-macbert-base	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	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	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	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	32.39	50.33	65.64	32.56	74.45	68.88	51.17	53.67	3138
CoSENT	BAAI/bge-large-zh-noinstruct	shibing624/text2vec-bge-large-chinese	38.41	61.34	71.72	35.15	76.44	71.81	63.15	59.72	844

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，数据集相对于shibing624/nli-zh-all/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
• shibing624/text2vec-base-multilingual模型，是用CoSENT方法训练，基于sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2用人工挑选后的多语言STS数据集shibing624/nli-zh-all/text2vec-base-multilingual-dataset训练得到，并在中英文测试集评估相对于原模型效果有提升，运行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，多语言语义匹配任务推荐使用
• shibing624/text2vec-bge-large-chinese模型，是用CoSENT方法训练，基于BAAI/bge-large-zh-noinstruct用人工挑选后的中文STS数据集shibing624/nli-zh-all/text2vec-base-chinese-paraphrase-dataset训练得到，并在中文测试集评估相对于原模型效果有提升，在短文本区分度上提升明显，运行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
• 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
• 各预训练模型均可以通过transformers调用，如MacBERT模型：--model_name hfl/chinese-macbert-base 或者roberta模型：--model_name uer/roberta-medium-wwm-chinese-cluecorpussmall
• 为测评模型的鲁棒性，加入了未训练过的SOHU测试集，用于测试模型的泛化能力；为达到开箱即用的实用效果，使用了搜集到的各中文匹配数据集，数据集也上传到HF datasets链接见下方
• 中文匹配任务实验表明，pooling最优是EncoderType.FIRST_LAST_AVG和EncoderType.MEAN，两者预测效果差异很小
• 中文匹配评测结果复现，可以下载中文匹配数据集到examples/data，运行 tests/model_spearman.py 代码复现评测结果
• QPS的GPU测试环境是Tesla V100，显存32GB

模型训练实验报告：实验报告

Usage (text2vec)

Using this model becomes easy when you have text2vec installed:

pip install -U text2vec

Then you can use the model like this:

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-bge-large-chinese')
embeddings = model.encode(sentences)
print(embeddings)

Usage (HuggingFace Transformers)

Without 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:

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-bge-large-chinese')
model = BertModel.from_pretrained('shibing624/text2vec-bge-large-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 is a popular library to compute dense vector representations for sentences.

Install sentence-transformers:

pip install -U sentence-transformers

Then load model and predict:

from sentence_transformers import SentenceTransformer

m = SentenceTransformer("shibing624/text2vec-bge-large-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)

Full Model Architecture

CoSENT(
  (0): Transformer({'max_seq_length': 256, 'do_lower_case': False}) with Transformer model: ErnieModel 
  (1): Pooling({'word_embedding_dimension': 1024, '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 https://huggingface.co/BAAI/bge-large-zh-noinstruct 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.

Citing & Authors

This model was trained by text2vec.

If you find this model helpful, feel free to cite:

@software{text2vec,
  author = {Ming Xu},
  title = {text2vec: A Tool for Text to Vector},
  year = {2023},
  url = {https://github.com/shibing624/text2vec},
}