-
Hello everyone. I was using the model a week ago without any problems. Today I am getting an error when trying to load Top2Vec with embedding_model parameter (without it works fine)
I get error lik…
-
## 一言でいうと
良質な文表現を得るために、BERTの学習を組み合わせた研究。Encode => Average Pooling => MLPで文表現を得た後、次文の入力に結合してMasked LMの学習を行う(文表現用と学習用Encoderは重みを共有する)。隣接文情報からのMask予測という点で文レベルのSkip Thoughtに近い。多言語NLPで優秀な精度。
![image]…
-
I want to train a model using this dataset so that when I feed it with _grammatically incorrect_ questions it should rate it. How can create such model?
-
I am using Google Colab to run on simple experiment.
The idea is to visulaize attention weights and predictions on text data.
Here is the code
```
!pip install witwidget
!pip install trans…
-
how can we use sentence encoder as siamese architecture to pass two sentences as input?
-
```python
embed = hub.load("https://tfhub.dev/google/universal-sentence-encoder-multilingual/3")
df2 = dd.from_pandas(pd.DataFrame({'ngram': ngrams_list}), npartitions=4)
csv_dask = dd.read_csv…
-
Hi @nreimers
I was testing English sentence similarity using other bert and roberta models but unexpectedly distiluse-base-multilingual-cased is giving me better accuracy. Can you please explain to …
-
Hi, thank you for your great work.
distiluse-base-multilingual-cased has one more dense layer compared to the pool-only model. How is this dense layer added?
We are constructing a Chinese long text…
-
Hi! I tried installing `pip install top2vec[sentence_encoders]` in a Jupyter notebook environment running in Anaconda in Windows 11, and getting the following error:
```
Defaulting to user installat…
-
你好，在使用数据库问题回答时，数据召回似乎正常，但rerank时报错了。
在chat_data-chatollama-1 的日志日这样的：
```
Knowledge base file created with ID: 2
URL: /api/models/chat User: null
Chat with knowledge base with id: 1
Knowledge …