GPT2-XL in run_convsent_llama2.py

[kailinjiang]

python examples/run_convsent_llama2.py --hparams_dir /home/jiangkailin/project/EasyEdit-main/hparams/FT/gpt2-xl.yaml --editing_method FT --data_dir /home/jiangkailin/project/EasyEdit-main/knowedit/convsent

0%| | 0/800 [00:01<?, ?it/s] Traceback (most recent call last): File "/home/jiangkailin/project/EasyEdit-main/examples/run_convsent_llama2.py", line 153, in metrics, editedmodel, = editor.edit( File "/home/jiangkailin/project/EasyEdit-main/../EasyEdit-main/easyeditor/editors/editor.py", line 156, in edit return self.edit_requests(requests, sequential_edit, verbose, kwargs) File "/home/jiangkailin/project/EasyEdit-main/../EasyEdit-main/easyeditor/editors/editor.py", line 332, in edit_requests edit_evaluation(all_metrics, request, edited_model, i, eval_metric, test_generation, icl_examples, kwargs) File "/home/jiangkailin/project/EasyEdit-main/../EasyEdit-main/easyeditor/editors/editor.py", line 310, in edit_evaluation all_metrics[idx].update(compute_sent_metric(self.model, edited_model, self.model_name, self.hparams, self.tok,metric_kwargs=kwargs["metric_kwargs"][idx], device=self.hparams.device)) File "/home/jiangkailin/project/EasyEdit-main/../EasyEdit-main/easyeditor/evaluate/personality_evaluate.py", line 40, in compute_sent_metric raise NotImplementedError("currently only support for llama") NotImplementedError: currently only support for llama

[littlefive5]

This code only supports llama. We may support GPT2-XL in the future.

[zxlzr]

Do you have any further questions?