Releases: shibing624/text2vec
1.2.9
1.2.9版本
-
支持多卡推理(多进程实现多GPU、多CPU推理),
text2vec
支持多卡推理(计算文本向量): examples/computing_embeddings_multi_gpu_demo.py -
新增命令行工具(CLI),可以无需代码开发批量获取文本向量:
pip install text2vec>=1.2.9
text2vec --input_file input.txt --output_file out.csv --batch_size 128 --multi_gpu True
Full Changelog: 1.2.8...1.2.9
1.2.8
1.2.8版本
-
支持多卡推理(多进程实现多GPU和多CPU推理),
text2vec
支持多卡推理(计算文本向量): examples/computing_embeddings_multi_gpu_demo.py -
新增命令行工具(CLI),可以无需代码开发批量获取文本向量:
pip install text2vec -U
text2vec --input_file input.txt --output_file out.csv --batch_size 16
Full Changelog: 1.2.4...1.2.8
1.2.4
v1.2.4版本
- 实现了BGE微调训练方法 ,支持自定义样本集训练 https://github.com/shibing624/text2vec/blob/master/examples/training_bge_model_mydata.py ;支持构建训练样本集 https://github.com/shibing624/text2vec/blob/master/examples/data/build_zh_bge_dataset.py ;支持使用C-MTEB评估 https://github.com/shibing624/text2vec/blob/master/tests/eval_C-MTEB.py
- 发布了中文匹配模型shibing624/text2vec-bge-large-chinese,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,相较于原模型在短文本区分度上提升明显。
Full Changelog: 1.2.3...1.2.4
v1.2.2
v1.2.2版本
- 发布了多语言匹配模型shibing624/text2vec-base-multilingual,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
英文匹配数据集的评测结果:
Arch | BaseModel | Model | English-STS-B |
---|---|---|---|
GloVe | glove | Avg_word_embeddings_glove_6B_300d | 61.77 |
BERT | bert-base-uncased | BERT-base-cls | 20.29 |
BERT | bert-base-uncased | BERT-base-first_last_avg | 59.04 |
BERT | bert-base-uncased | BERT-base-first_last_avg-whiten(NLI) | 63.65 |
SBERT | sentence-transformers/bert-base-nli-mean-tokens | SBERT-base-nli-cls | 73.65 |
SBERT | sentence-transformers/bert-base-nli-mean-tokens | SBERT-base-nli-first_last_avg | 77.96 |
CoSENT | bert-base-uncased | CoSENT-base-first_last_avg | 69.93 |
CoSENT | sentence-transformers/bert-base-nli-mean-tokens | CoSENT-base-nli-first_last_avg | 79.68 |
CoSENT | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | shibing624/text2vec-base-multilingual | 80.12 |
- 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 |
Instructor | hfl/chinese-roberta-wwm-ext | 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 | 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 | 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
Full Changelog: 1.2.1...1.2.2
v1.2.1
v1.2.1
- 更新了中文匹配模型
shibing624/text2vec-base-chinese-nli
为新版shibing624/text2vec-base-chinese-sentence,针对CoSENT的loss计算对排序敏感特点,人工挑选shibing624/nli-zh-all并整理出高质量的有相关性排序的STS数据集shibing624/nli-zh-all/text2vec-base-chinese-sentence-dataset,在各评估集表现相对之前有提升; - 发布了适用于s2p的中文匹配模型shibing624/text2vec-base-chinese-paraphrase
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 |
Instructor | hfl/chinese-roberta-wwm-ext | 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 | 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 |
- 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,SOHU数据集 https://huggingface.co/datasets/shibing624/sts-sohu2021
Full Changelog: 1.2.0...1.2.1
v1.2.0
v1.2.0版本
-
发布了中文匹配模型shibing624/text2vec-base-chinese-nli,基于ERNIE-3.0-base模型,使用了中文NLI数据集shibing624/nli_zh全部语料训练的CoSENT文本匹配模型,在各评估集表现提升明显。
-
发布了2个中文NLI数据集:shibing624/snli-zh 和 shibing624/nli-zh-all
-
本项目release模型的中文匹配评测结果:
Arch | BaseModel | Model | ATEC | BQ | LCQMC | PAWSX | STS-B | Avg | QPS |
---|---|---|---|---|---|---|---|---|---|
Word2Vec | word2vec | w2v-light-tencent-chinese | 20.00 | 31.49 | 59.46 | 2.57 | 55.78 | 33.86 | 23769 |
SBERT | xlm-roberta-base | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | 18.42 | 38.52 | 63.96 | 10.14 | 78.90 | 41.99 | 3138 |
CoSENT | hfl/chinese-macbert-base | shibing624/text2vec-base-chinese | 31.93 | 42.67 | 70.16 | 17.21 | 79.30 | 48.25 | 3008 |
CoSENT | hfl/chinese-lert-large | GanymedeNil/text2vec-large-chinese | 32.61 | 44.59 | 69.30 | 14.51 | 79.44 | 48.08 | 2092 |
CoSENT | nghuyong/ernie-3.0-base-zh | shibing624/text2vec-base-chinese-nli | 51.26 | 68.72 | 79.13 | 34.28 | 80.70 | 62.81 | 3066 |
- 本项目release的数据集:
Dataset | Introduce | Download Link |
---|---|---|
shibing624/nli-zh-all | 中文语义匹配数据合集,整合了文本推理,相似,摘要,问答,指令微调等任务的820万高质量数据,并转化为匹配格式数据集 | https://huggingface.co/datasets/shibing624/nli-zh-all |
shibing624/snli-zh | 中文SNLI和MultiNLI数据集,翻译自英文SNLI和MultiNLI | https://huggingface.co/datasets/shibing624/snli-zh |
shibing624/nli_zh | 中文语义匹配数据集,整合了中文ATEC、BQ、LCQMC、PAWSX、STS-B共5个任务的数据集 | https://huggingface.co/datasets/shibing624/nli_zh or 百度网盘(提取码:qkt6) or github |
- 基于更大数据集shibing624/nli-zh-all的CoSENT匹配模型在训练中。
Full Changelog: 1.1.8...1.2.0
1.1.4
v1.1.4版本
发布了中文匹配模型shibing624/text2vec-base-chinese,基于中文STS训练集训练的CoSENT匹配模型。
- 本项目release模型的中文匹配评测结果:
Arch | BaseModel | Model | ATEC | BQ | LCQMC | PAWSX | STS-B | Avg | QPS |
---|---|---|---|---|---|---|---|---|---|
Word2Vec | word2vec | w2v-light-tencent-chinese | 20.00 | 31.49 | 59.46 | 2.57 | 55.78 | 33.86 | 23769 |
SBERT | xlm-roberta-base | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | 18.42 | 38.52 | 63.96 | 10.14 | 78.90 | 41.99 | 3138 |
CoSENT | hfl/chinese-macbert-base | shibing624/text2vec-base-chinese | 31.93 | 42.67 | 70.16 | 17.21 | 79.30 | 48.25 | 3008 |
Full Changelog: 1.1.3...1.1.4
add word2vec tencent light embeddings file: light_Tencent_AILab_ChineseEmbedding.bin
1.1.3
Full Changelog: 1.1.2...1.1.3
1.1.2
add dataset of nli_zh
1.1.0
重写了CoSENT, SentenceBERT模型的训练和预测代码:
- 句子匹配模型训练逻辑继承基类SentenceModel,
- 新增train_model, eval_model, 代码结构更清晰,
- 预测均使用基类的encode实现。