danielmisrael
danielmisrael
I would like to cite those algorithms or this package. Specifically for constant volume bin packing.
For Multi-DocumentQA is there a simple way to know which passages are being retrieved from for a given answer? It would be very helpful to have a field called 'retrieval_indices'...
``` from transformers import AutoModelForCausalLM, AutoTokenizer import torch model = AutoModelForCausalLM.from_pretrained("EleutherAI/pythia-160m") tokenizer = AutoTokenizer.from_pretrained("EleutherAI/pythia-160m") input_ids = tokenizer.encode("Hello, my dog is cute", return_tensors="pt") model.eval() with torch.no_grad(): logits = model(input_ids).logits print(logits) print(torch.topk(logits,...