Ashim Gupta

Label probabilities for the CRF layer

4

Hi, Thanks for sharing this great implementation. I know it is possible to get the label probabilities using forward backward algorithm in CRFs. I am finding some difficulties in implementing/modifying...

First, thank you for releasing your code. I am trying to reproduce results of your paper. I am running `NLI_KD_training.py` for MRPC with DEBUG=True. The setting I am running is...

Tensorized Matrices vs Factorized Tensors

1

Hi, Thanks for creating and maintaining this library. I had a couple of basic questions, would be great if you could answer: 1. What is the difference between the files...

Multi GPU inference

5

## ❓ Question Hi, I am trying to run zero-shot evaluation for the 30 billion `llama-30b`. Even for a `batch_size = 1`, I am getting a `torch.cuda.OutOfMemoryError: CUDA out of...

Hi @ChristophAlt , Thank you for the wonderful codebase. I see that for reporting macro averaged F1 scores, you first calculate macro averaged precision, then calculate macro averaged recall, and...

LDR for rectangular matrices.

1

Hi @tridao , Thanks for this implementation. Everywhere in the code I notice that the weight matrices are assumed to be square. Did you guys perform any experiments with rectangular...

Benchmarking GLUE tasks for in-context learning

2

## ❓ Question I am trying to benchmark `llama-2-7b` on the GLUE benchmark for in-context learning. But the accuracy I get for MNLI (`mismatched validation`) is 35.22 for both zero-shot...

Hi, I am trying to reproduce the experiments of your paper. I think `types_annotated/` directory is missing. Also If possible can you write a brief Readme with instructions on how...

Hi , I wanted to run your code for a gene/protein tagger. So I downloaded and extracted the zip file from Quick Start section. I was running the code to...