Closed AmitRozner closed 3 months ago
The IKE method requires providing some cases as examples. Therefore, when running it, you need to include the train_data_path parameter, similar to the MEND and SERAC methods.
Hi, have you solved your issue?
I tried with KnowEdit/benchmark/wiki_counterfact/train_cf.json
how much GPU memory is required for llama-7b? I am trying with A100 40gb and getting OOM.
Also, what is the file for ZsRE? I tried zsre/zsre_mend_train_10000.json
but getting an error:
"prompt": record["prompt"] if "prompt" in record else record["text"], KeyError: 'text'
run_knowedit_llama2.py is prepared for KnowEdit, so your dataset should be selected in KnowEdit. You can download it from https://huggingface.co/datasets/zjunlp/KnowEdit. If you encounter an out-of-memory error, you can reduce the value of k in the hparams.
Hi, have you solved your issue?
I lowered K and was able to run it partially. Need to get an 80GB GPU to run everything.
Hi, I am trying to run IKE on counterfact dataset using the following command:
python run_knowedit_llama2.py \ --editing_method=IKE \ --hparams_dir=../hparams/IKE/llama-7b \ --data_dir=./data \ --datatype='counterfact'
Sincetrain_data_path
is not set it is breaking at:train_ds = KnowEditDataset(args.train_data_path)
The error is due totrain_data_path
beingNone
:TypeError: expected str, bytes or os.PathLike object, not NoneType
Any advice? Thanks