GPT2LMHeadModel.from_pretrained('gpt2') not loading attn weights

I am following the examples here. Specifically, this one:

import torch
from transformers import GPT2Tokenizer, GPT2LMHeadModel
tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
model = GPT2LMHeadModel.from_pretrained('gpt2')
inputs = tokenizer("Hello, my dog is cute", return_tensors="pt")
outputs = model(**inputs, labels=inputs["input_ids"])
loss, logits = outputs[:2]

When I run the code, I get this warning:

Some weights of GPT2LMHeadModel were not initialized from the model checkpoint at gpt2 and are newly initialized: ['h.0.attn.masked_bias', 'h.1.attn.masked_bias', 'h.2.attn.masked_bias', 'h.3.attn.masked_bias', 'h.4.attn.masked_bias', 'h.5.attn.masked_bias', 'h.6.attn.masked_bias', 'h.7.attn.masked_bias', 'h.8.attn.masked_bias', 'h.9.attn.masked_bias', 'h.10.attn.masked_bias', 'h.11.attn.masked_bias', 'lm_head.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

I am wondering if I should maybe point to some specific file to have the weights loaded?

BTW I see some friendly faces on these forums! :blush: Hi @sshleifer and @sgugger! :wave:

Hi @radek, good to see you here!

This is a known issue that is currently being addressed by #5922 (under review). You can safely discard the warning.

1 Like