shabie
shabie
Haha thank you for this issue! Tagging @uakarsh since both of us have managed to get the architecture largely down (we think!) It would be awesome to get this integrated...
> > > Hi, > > DocFormer would indeed be a great addition to the library. Note that pretrained weights are required for a model to be added. > >...
Do these fine details matter so much?
I ran into the same problem and ruined my 6-days of pre-training because I wrongly assumed that `do_lower_case=False` would be set given that I am using the cased version of...
I'll try to get on it in the next days. On Fri, Nov 19, 2021, 10:26 uakarsh ***@***.***> wrote: > I am trying it, however, I face this error >...
So as an update, despite my best attempts I haven't manage to get the OCR any bit faster...
Bedrock's parameters are provider specific and Langchain makes no attempt to unify them (which will anyways be a bad idea). So I am not sure how much introduction of Langchain...
Would be great to have something that works with boto3 too. I am happy to make a PR.
There are now models in Bedrock that return logits in different forms. Here are a couple of examples: 1. Cohere's command model: https://docs.cohere.com/reference/generate 2. AI21's jurassic model: https://docs.ai21.com/reference/j2-complete-ref Sadly, Claude...
>From the comments, it looks like ONLY training samples from dataset_1, dataset_2, and dataset_3 are considered. There isn't explanation how each dataset contributes to the test_xxx split. Each dataset should...