Santhosh

Beam Search Is very Slow in Transformer

2

I have been using beam size of 3 and alpha 1.0 for beam search decoding looks like it is very slow . Greedy search takes around 30-40 seconds for generating...

GPT-2 Generate multiple words using past

2

ort_inputs = dict((sess.get_inputs()[i].name, np.expand_dims(input, 0)) for i, input in enumerate(inputs)) res = sess.run(None, ort_inputs) In pytorch i iterate over a for loop to generate the multiple words.How can the same...

How to use multiple prefix tuned models with parallel inference.

1

Hi Library error when I use muliptle prefix tuned models for parallel inference. What are the adpaters which supports parallel inference and how to know their configuration. Thanks

How does this scale

1

How do you think NN based similarity will scale to millions of documents?

what changes needs to be made to scrape the paragraph under this question?

1

Example: for the following scrapped query: How do you find the cheapest airfare? i also need the paragraph . To find the cheapest airfare, you can visit our site or...