[BUG]:chatgpt inference still ERROR after fix

[wac81]

🐛 Describe the bug

still error：

size mismatch for transformer.ln_f.weight: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for transformer.ln_f.bias: copying a param with shape torch.Size([768]) from checkpoint, the shape in current model is torch.Size([64]). size mismatch for lm_head.weight: copying a param with shape torch.Size([50257, 768]) from checkpoint, the shape in current model is torch.Size([250880, 64]).

params： parser.add_argument('--model', default='bloom', choices=['gpt2', 'bloom', 'opt']) parser.add_argument('--pretrain', type=str, default='./actor_checkpoint_prompts.pt')

Environment

No response

[wac81]

File "inference.py", line 56, in eval(args) File "inference.py", line 21, in eval actor.model.load_state_dict(state_dict) File "/home/rst/ColossalAI/env/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1671, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(

[ht-zhou]

Thanks for your feedback, can you show your command line code please？

[wac81]

python inference.py --pretrain ./actor_checkpoint_prompts.pt --model bloom

[wac81]

if i use gpt2 to train , i get right results, bloom is not right any way.