Shanya Sharma

Hi, has there been a fix to this since we have been facing this issue with Python 3.10

Hi @jzf2101 I have removed the prompts which don't contribute to the original task and made some minor changes to prompts to make them sound less technical. Regarding rendering of...

Thanks for reviewing the prompts @stephenbach . I have fixed the bug in the templates where the values were not rendering correctly. > I also don't think the `table_to_text` prompt...

Does this work?

``` def calc_ppl(sentence): tokenize_input = tokenizer.encode(sentence) tensor_input = torch.tensor([tokenize_input]) loss=model(tensor_input, labels=tensor_input)[0] return np.exp(loss.detach().numpy()) def eval_website_desc(orig_text, orig_website_desc, website_desc_list): """ Our goal is to evaluate the ppl of orig_website_desc ||| orig_text >...

Toxicity Eval using RTP Prompts (https://colab.research.google.com/drive/1KbMgBlJshvNgPsZBRn0SUIVKSLRwmPra?usp=sharing ) Though on analysis I found that this might not be the best dataset so I'm also working on evaluating bias using the BOLD...

does #42 serve half of the purpose (saving the model)?