karpathy / minGPT

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
MIT License
20.16k stars 2.51k forks source link

error line 200, in from_pretrained assert len(keys) == len(sd) #128

Open Sandy4321 opened 9 months ago

Sandy4321 commented 9 months ago

error line 200, in from_pretrained assert len(keys) == len(sd)

len(keys) 581 len(sd) 629

image

mingpt-master\mingpt-master\mingpt\model.py", line 200, in from_pretrained assert len(keys) == len(sd)

windows 11 OS torch version 1.13.1 transformers version 4.36.2

Sandy4321 commented 9 months ago

Python 3.10.11

Sandy4321 commented 9 months ago

code import torch from transformers import GPT2Tokenizer, GPT2LMHeadModel from mingpt.model import GPT from mingpt.utils import set_seed from mingpt.bpe import BPETokenizer set_seed(3407)

use_mingpt = True # use minGPT or huggingface/transformers model? model_type = 'gpt2-xl' device = 'cuda' if use_mingpt: model = GPT.from_pretrained(model_type) else: model = GPT2LMHeadModel.from_pretrained(model_type) model.config.pad_token_id = model.config.eos_token_id # suppress a warning

ship model to device and set to eval mode

model.to(device) model.eval();

q = 0

Sandy4321 commented 9 months ago

mingpt-master\mingpt-master\s_mingpt_jan21.py", line 15, in model = GPT.from_pretrained(model_type) File "c:\mingpt-master\mingpt-master\mingpt\model.py", line 200, in from_pretrained assert len(keys) == len(sd)

builtins.AssertionError

xiaoyuxie-vico commented 9 months ago

I have the same issue.

Sandy4321 commented 9 months ago

MAY @karpathy FIX IT ?

chenokay commented 6 months ago

is it fixed?

vanduc103 commented 6 months ago

It was fixed in here #120 and also the reason of the error.