-
Hello!
I have a text mining use-case with one overarching document set, consisting of many smaller sub-sets of documents.
i want to train a topic model for each smaller sub-set of documents, but t…
-
> In the document [ML commons](https://opensearch.org/docs/latest/ml-commons-plugin/api/) shows how to upload a model and host this model by OpenSearch. It just gives a use case of SBERT written by T…
-
When using HuggingFaceEmbeddings in LangChain to embed documents, I noticed that the embedding process takes significantly longer on the server compared to my local machine. My local computer has only…
-
I have a corpus with 144,491 entries with around 2000 characters each forming phrases in english and german.
Each entry in monolingual.
My goal is to enter a query like a question or a set of ke…
-
Hi Nils,
from this documentation [here](https://www.sbert.net/docs/package_reference/losses.html#cosinesimilarityloss) in the screenshot picture cosine-sim(u,v) is given the range [-1,1], however, th…
-
Hi,
Thanks for providing an example of training SBERT on NLI examples.
I have a question on the example code provided `training_nli.py`
At line: `train_loss = losses.SoftmaxLoss(model=model,…
-
Hi,
I started using SBert for embeddings to use for similarity dot products. However, our system is very resource constrained, and I'm wondering if the embeddings part of the model can be easily ex…
-
Hi I noticed in paper 'Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks', you used avg. BERT embedding to compare with your new model SBERT. I created average word embeddings in the last…
-
```
2024-02-23 15:51:23 Starting Danswer Api Server
2024-02-23 16:01:40 Starting Danswer Api Server
2024-02-23 15:51:21 INFO [alembic.runtime.migration] Context impl PostgresqlImpl.
2024-02-23 15…
-
Because the cross encoder simply use AutoModelForSequenceClassification which is
same as the standard classify model in https://docs.adapterhub.ml/training.html
adapter-hub is also a outstanding fr…