setfit
                                
                                 setfit copied to clipboard
                                
                                    setfit copied to clipboard
                            
                            
                            
                        Efficient few-shot learning with Sentence Transformers
Can we use this for code generation?
I understood that setfit is a light weight solution for few shot learning. Two questions came up: .) What would be a number of samples of class you would switch...
Hello, I would like to test this promising framework on a similarity classification task. So basically, I have got a dataset with 3 columns: (sentence1,sentence2,label). From what I understand, currently...
The current SetFit implementation combines the embeddings of a frozen body, with the learnable parameters of a logistic regression classifier. It would be desirable to have a PyTorch implementation that...
Hi, just looking to see if checkpoints are implemented with the SetFitTrainer. Couldn't find it, unlike how the normal models in Hugging Face use `output_dir` for saving checkpoints when training...
Hi! I wanted to ask if there was an in-built function to get the probability value of predicted output from a classification task, something like predict_proba() from sklearn? From what...
Hi there! I was wondering whether you can provide a range for typically "good" values to use/test for the argument num_epochs both in the single label classification case and the...
Hi, Thanks for sharing this work. I am wondering if it is possible to run evaluation dataset to tune hyperparameters. The SetFitTrainer doesn't seem to accept arguments like 'evaluation_strategy', 'save_strategy',...
In our paper, we used knowledge distillation to compress a SetFit model into a smaller student. This logic is currently implemented as a [script](https://github.com/huggingface/setfit/blob/main/scripts/setfit/run_fewshot_distillation.py), but it would be valuable to...
Hello, Can this library be used for fine-tuning a question-answering model with small amount of data as well ? I have a data that is in the same format with...