BAOOOOOM

The meaning of Prefix-tuning state_dict that OpenPrompt added.

1

Hello, thanks for the great program, it saves me a lot of time and energy. But I have a question about state_dict when using prefix_tuning_template in T5. I find that...

[BUG]an error will occur when running t5-3b in prefixtuning.

5

Hello, when I use the config that "plm, tokenizer, model_config, WrapperClass = load_plm('t5', 't5-3b'), PrefixTuningTemplate", it will rise the error like below. But if I run the programe using model...

Your project is meaningful and practical, I learn a lot from it. I don't understand why we add 'new_token_len' when we already have 'm_prefix_len', thank you very much.  

Multiple-Choice question like CSQA dataset require select one choice from candidate choice. The previous approach was to input questions and train on the answers as labels. In the testing phase,...

Some question in ./prompts/prefix_tuning_template.py

1

In process_batch module, why creat a past_key_values in batch_size=1 and then use expand to batchsize?

Code about augmenting questions with Google snippets

2

Hello, can you provide the code about finding and using Google snippets to augmenting questions. Thanks!

Thanks for your wonderful work! I think it is very interesting and meaningful, so I want to follow your work. Could you please tell me when the code can be...