search

huggingface / transfer-learning-conv-ai

🦄 State-of-the-Art Conversational AI with Transfer Learning
MIT License
1.73k stars 431 forks source link

Problem running interact.py #72

Closed parthplc closed 4 years ago

parthplc commented 4 years ago 
Traceback (most recent call last):
  File "question-generation/interact.py", line 238, in <module>
    run()
  File "question-generation/interact.py", line 144, in run
    model = GPT2LMHeadModel.from_pretrained(args.model_checkpoint)
  File "/opt/conda/lib/python3.6/site-packages/pytorch_pretrained_bert/modeling_gpt2.py", line 475, in from_pretrained
    "Error(s) in loading state_dict for {}:\n\t{}".format(model.__class__.__name__, "\n\t".join(error_msgs))
RuntimeError: Error(s) in loading state_dict for GPT2LMHeadModel:
    size mismatch for transformer.wte.weight: copying a param with shape torch.Size([50265, 768]) from checkpoint, the shape in current model is torch.Size([50257, 768]).
    size mismatch for lm_head.decoder.weight: copying a param with shape torch.Size([50265, 768]) from checkpoint, the shape in current model is torch.Size([50257, 768]).

I am able to run easily on local machine but when I tried running on Google colab it throws this error. I am not sure what is wrong.

princebaretto99 commented 4 years ago

Same Issue . Kindly Inform if anyones knows the solution