Downloads · 30 days
70
8% of all-time downloads
text2vec-roberta-512
EricLee/text2vec-roberta-512
text2vec-roberta-512 is a sentence similarity model from EricLee. Use it when you need a score for how close two texts are. It is set up for transformers. The card lists the license as apache-2.0.
简介： 参考 https://github.com/shibing624/text2vec 基于Cosent模型架构，使用hfl/chinese-roberta-wwm-ext作为基座模型，在中文STS-B数据集上重新微调训练，将maxseqlength从原有的128扩展到了512 evalspearman:0.833
All-time downloads
825
Public
Repo size
818 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin409 MB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jun 6, 2023
- Updated
- Jun 6, 2023
- SHA
- f033a372
Datasets
Model card
From the Hugging Face model README
简介： 参考 https://github.com/shibing624/text2vec 基于Cosent模型架构，使用hfl/chinese-roberta-wwm-ext作为基座模型，在中文STS-B数据集上重新微调训练，将max_seq_length从原有的128扩展到了512 eval_spearman:0.833
下游任务： 基于text2vec库或sentence-transformer库均可调用。 文本向量表征：
>>> from text2vec import SentenceModel, EncoderType
>>> model = SentenceModel('EricLee/text2vec-roberta-512', encoder_type=EncoderType.FIRST_LAST_AVG, max_seq_length=512)
>>> model.encode("今天天气不错啊")
Embedding shape: (768,)
- Task
- Sentence Similarity
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- zh
- Created
- Jun 6, 2023
- Updated
- Jun 6, 2023