Andyxht020510
commented
2 weeks ago 把mom2_adjustment:改为true后，运行出现RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable.
XeeKee
没有修改过代码 import os import os.path import sys import json import random sys.path.append('..') from easyeditor import BaseEditor from easyeditor import ROMEHyperParams
prompts = ['Ray Charles, the', 'Grant Hill is a professional', 'The law in Ikaalinen declares the language' ] ground_truth = ['piano', 'basketball', 'Finnish' ] target_new = ['violin', 'soccer', 'Swedish' ] subject = ['Ray Charles', 'Grant Hill', 'Ikaalinen' ]
hparams = ROMEHyperParams.from_hparams('../hparams/ROME/gpt2') editor = BaseEditor.from_hparams(hparams) metrics, editedmodel, = editor.edit( prompts=prompts, ground_truth=ground_truth, target_new=target_new, subject=subject, keep_original_weight=False )
print(''100)
from transformers import GPT2Tokenizer from transformers import GPT2LMHeadModel
tokenizer = GPT2Tokenizer.from_pretrained('./hugging_cache/gpt2') tokenizer.pad_token_id = tokenizer.eos_token_id tokenizer.padding_side='left' generation_prompts = [ "Ray Charles, the", "The law in Ikaalinen declares the language" ]
model = GPT2LMHeadModel.from_pretrained('./hugging_cache/gpt2').to('cuda') batch = tokenizer(generation_prompts, return_tensors='pt', padding=True, max_length=50)
pre_edit_outputs = model.generate( input_ids=batch['input_ids'].to('cuda'), attention_mask=batch['attention_mask'].to('cuda'), max_new_tokens=3 ) post_edit_outputs = edited_model.generate( input_ids=batch['input_ids'].to('cuda'), attention_mask=batch['attention_mask'].to('cuda'), max_new_tokens=3 ) print('Pre-Edit Outputs: ', [tokenizer.decode(x) for x in pre_edit_outputs.detach().cpu().numpy().tolist()]) print('Post-Edit Outputs: ', [tokenizer.decode(x) for x in post_edit_outputs.detach().cpu().numpy().tolist()])
yaml： alg_name: "ROME" model_name: "./hugging_cache/gpt2" stats_dir: "./data/stats" device: 0 layers: [9] fact_token: "subject_last" v_num_grad_steps: 23 v_lr: 5e-1 v_loss_layer: 11 v_weight_decay: 0.0015 clamp_norm_factor: 4 kl_factor: 0.0625 mom2_adjustment: false context_template_length_params: [[5, 10], [10, 10]] rewrite_module_tmp: "transformer.h.{}.mlp.c_proj" layer_module_tmp: "transformer.h.{}" mlp_module_tmp: "transformer.h.{}.mlp" attn_module_tmp: "transformer.h.{}.attn" ln_f_module: "transformer.ln_f" lm_head_module: "transformer.wte" mom2_dataset: "wikipedia" mom2_n_samples: 1000 mom2_dtype: "float32"