Hi, I have a local Python 3.8 conda environment with tensorflow and transformers installed with pip (because conda does not install transformers with Python 3.8) But I keep getting warning messages like “Some layers from the model checkpoint at (model-name) were not used when initializing (…)” Ev…

Message "Some layers from the model were not used"

sgugger November 11, 2020, 1:11pm 2

Tagging @jplu so he’s aware, this looks like a bug (but you can proceed safely, the bug is that there is a warning when there should be nothing).

Topic		Replies	Views
"Some weights were not used" message with AutoModel Beginners	4	2009	May 21, 2024
No weights has been used to initialize the model 🤗Transformers	0	353	February 26, 2023
Loading pytorch_pretrained_bert models with transformers Beginners	2	1903	April 29, 2021
Some weights of the model checkpoint at /Flaubert/finetune/Multiclass/checkpoint-10 were not used when initializing Flaubert ForSequenceClassification: 🤗Transformers	0	361	December 13, 2021
XLNetForSqeuenceClassification warnings 🤗Transformers	16	4269	April 3, 2021