Pietro Lesci

This PR has 2 goals: - dockerize quica (flask) webapp -> we need the app code into an `/app` folder - use java backend for mace The quica library will...

🚀 Add FLOPs count to model summary

8

## 🚀 Feature Add FLOPs count in model summary. ### Motivation Improvements in model development are increasingly evaluated using the FLOPs count (e.g., [Training Compute-Optimal Large Language Models](https://arxiv.org/pdf/2203.15556.pdf)). However, there...

Problems after upgrading to 2.6.1

10

### Describe the bug Loading a dataset_dict from disk with `load_from_disk` is now creating a `KeyError "length"` that was not occurring in v2.5.2. Context: - Each individual dataset in the...

Pipe ("|") separated slot values

2

Hi there, I am using this version of the dataset and I have noticed that for 436 dialogue turns there are slot values that are separated by a pipe ("|")....

### Anthology ID 2024.naacl-long.467 ### Type of Change Revision ### PDF of the Revision or Erratum [[v2] AnchorAL__Computationally_Efficient_Active_Learning_for_Large_and_Imbalanced_Datasets.pdf](https://github.com/user-attachments/files/15917471/v2.AnchorAL__Computationally_Efficient_Active_Learning_for_Large_and_Imbalanced_Datasets.pdf) ### Brief Description of Changes Revised the related work in sec. 2.3.

🌟Appreciation🌟

1

Hi there, This is a brief message of appreciation to @bernardodionisi and contributors for developing this library. We use (and cite) this software in our latest paper on memorisation in...

Allow users to select/write encoding strategies

2

Hi there, **Do you plan to add the possibility to control how tokenizers behave at inference time?** For example, adding the possibility for the user to decide whether to use...