Philip May

Hi. I do not fully understand the meaning of `--blanks-separate-docs`. I know that this is important for "next sentence prediction" with normal BERT. But I do not think that this...

Normalize before using LogisticRegression

1

Hi, as far as I can see is that setfit applies LogisticRegression on top of the output of the sentence transformer model. See here: https://github.com/huggingface/setfit/blob/7735e8e3b208edb8dfb549beb16e585453c5f44e/src/setfit/modeling.py#L49-L55 The problem I see is...

Use amp / FP16

2

Hi, since the sentence transformers support FP16 training (by setting `use_amp=True`) can this also be build in here? Not sure if this is a FR or a question. :-)

Hi, imo because of dry principle this function: https://github.com/huggingface/setfit/blob/7735e8e3b208edb8dfb549beb16e585453c5f44e/src/setfit/modeling.py#L61-L63 should just redirect to predict. Because of dry principle. Like this: ``` def __call__(self, inputs): return self.predict(inputs) ``` I can provide...

PR to solve #129

[FR] add documentation about the `loss_class` selection

2

Can you please add documentation about the `loss_class` selection? There seems to be a new loss class implemented called `SupConLoss`. Maybe you could add some documentation how to select them...

`privileged: true` is missing for `cadvisor/docker-compose.yml`

1

Hi, first, many thanks for your super helpful videos. In the config IMO there is this `privileged: true` missing. Without it I am getting this in the logs: ``` Could...

Hi, does this integrate with Jupyter Lab notebooks? Thanks Philip

Multilingual prompt templates

1

Hi, I plan to use LangChain for German use-cases. Do you already have multilingual prompt templates or plan to create them? Otherwise this might be a first contribution from my...

Problem with sql_chain and quotation marks

6

Hi, I observed an issue with sql_chain and quotation marks. The SQL that was send had quotation marks around and triggered an error in the DB. This is the DB...