Muhammad Khalifa
Muhammad Khalifa
@zeeshansayyed Thank you for your interest to contribute. what I did here is simply use the masked language modeling architectures (encoders) and tweaked them a bit for sequence tagging in...
@rvj07ai Are you still working on this feature? I'm thinking of starting on it.
Yes, it certainly is possible, although I did not observe significant (if any) performance gain from using CRFs
Thanks for the response. This happens with HotpotQA when I run the following command or similar commands. ``` python run_graph_retriever.py \ --task hotpot_open \ --bert_model bert-base-uncased --do_lower_case \ --dev_file_path path/to/hotpotqa/dev...
Any update on this? I am having the same issue
@reciprocated is there a way now to use a reward function of the form `reward_fn(samples, prompts, outputs)`?
any update on this?
Any update on this?