-
'shibing624/text2vec-base-chinese'是huggingface下载量超高的一个中文库，比sbert 的那个多语言库准确度高很多，看不到你说的两部分，sentence_transform 也支持，有办法加速吗
-
Hi,
I created two classes : **Card, Benefit**
- **Card** class has _card_name_, _card_company_, and _benefits_ properties which is cross reference to **Benefit** class.
- **Benefit** class ha…
-
### Search before asking
- [X] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues.
### Operating system information
Linux
### P…
-
### 🐛 bug 说明
m3e生成一组数据的embedding需要15秒，而text2vec只需要2秒。
### Python Version
other
-
您好，我看您的文档中支持模型的微调，可否对于shibing624/text2vec-base-multilingual模型举一个具体的例子，比如如何feed数据等
cjji updated
11 months ago
-
您好，请问下fine-tuning第一阶段的unlabel的数据集，正样本是自己，负样本是随机在batch里面选取的吗？看到readme中还说了用text2vec进行简单负样本的过滤，好像这一阶段在代码里面没有体现，具体的论文中好像也没看到。
-
I am trying to add a Property to a Class with the propertyCreator, but I always recieve a Error, which I do not understand correctly.
`return await this.weaviateClient.schema
.propertyCreato…
-
I installed a GKE cluster with 2 replicas. Weaviate 1.17.4
After any update of the configuration (adding a module, upgrading from Weaviate 1.17.1 to 1.17.4), I get the following error:
But I…
-
模型中max_seq_length指的应该是模型能处理的最大token数，我想问下，这个模型中的token跟汉字字符是一个大概什么样比例的换算关系，我在一个博客上看到在text2vec上是1token约等于1.5个汉字，请问这个结论对吗？
-
运行 chatpdf.py 时报错：
```bash
torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 12.00 MiB (GPU 0; 5.79 GiB total capacity; 5.05 GiB already allocated; 13.88 MiB free; 5.11 GiB reserved…