# How to load a torch model with transformers? **URL:** \ **Category:** 🤗Transformers\ **Created:** [September 7, 2022, 7:20pm UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699 "2022-09-07T19:20:14Z")\ **Posts on this page:** 6\ **Page:** 1
**Author:** ![SickBoy](https://avatars.discourse-cdn.com/v4/letter/s/7ea924/32.png) [@SickBoy](https://discuss.huggingface.co/u/SickBoy)\ **Post date:** [September 7, 2022, 7:20pm UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/1 "2022-09-07T19:20:14Z")
Hello Hello, I previously fine-tuned a sentiment analysis model with pytorch, when I saved the model I did it with a .pth extension as recommended by pytorch. I want to use this model remotely and I uploaded it to hugging face hub, but when uploading it with “AutoModelForSequenceClassification” I get an error saying it must be in extension .bin. What should I do to use this model? ---
**Author:** ![NimaBoscarino](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nimaboscarino/32/4358_2.png) [@NimaBoscarino](https://discuss.huggingface.co/u/NimaBoscarino)\ **Post date:** [September 7, 2022, 8:19pm UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/2 "2022-09-07T20:19:42Z")
Hello! Can you link to the model on the Hub? I can take a quick look at it 😊 I believe that the `.bin` extension is just a convention. You should be able to just rename your `.pth` file to be `pytorch_model.bin`. Can you try that and see if it loads the weights? ---
**Author:** ![SickBoy](https://avatars.discourse-cdn.com/v4/letter/s/7ea924/32.png) [@SickBoy](https://discuss.huggingface.co/u/SickBoy)\ **Post date:** [September 8, 2022, 1:11am UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/3 "2022-09-08T01:11:56Z")
Hello I tried changing the name of the file but it didn’t work, now I have even more doubts, as I understand when loading the model with `AutoModelForSequenceClassification`it takes the `config.json` file for the configuration and then the `.bin` file to load the weights. When I train the model, create a class like the following to define the model: ```auto class BERTSentimentClassifier(nn.Module): def __init__ (self,n_clases): super(BERTSentimentClassifier,self). __init__ () self.bert = BertModel.from_pretrained(model_name, return_dict = False) self.drop = nn.Dropout(p=0.35) self.linear = nn.Linear(self.bert.config.hidden_size, n_clases) def forward (self,input_ids,attention_mask): _,cls_output = self.bert( input_ids = input_ids, attention_mask = attention_mask ) drop_out = self.drop(cls_output) output = self.linear(drop_out) return output ``` By doing this, my model doesn’t have a config attribute, it has a bert layer and this one does have a config attribute, but it’s not the entire model configuration. Because of this and because of the model extension, I can’t load my model from the hub. I don’t know what I have to do to use my model from the hub. This is the link to the model: [https://huggingface.co/SickBoy/analisis-sentimiento-spanish-eds](https://huggingface.co/SickBoy/analisis-sentimiento-spanish-eds) ---
**Author:** ![NimaBoscarino](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/nimaboscarino/32/4358_2.png) [@NimaBoscarino](https://discuss.huggingface.co/u/NimaBoscarino)\ **Post date:** [September 8, 2022, 2:00am UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/4 "2022-09-08T02:00:08Z")
Ah I see! The `BertForSequenceClassification` class is [basically the same as yours](https://github.com/huggingface/transformers/blob/02b176c4ce14340d26d42825523f406959c6c202/src/transformers/models/bert/modeling_bert.py#L1514), so I think instead of creating your own class when training the model, you would need to create it as ```python model = BertForSequenceClassification.from_pretrained(model_name, num_labels=n_classes) ``` (Pulled from [Fine-tune a pretrained model](https://huggingface.co/docs/transformers/training#train)) If you want to set a value for `nn.Dropout` you can pass also pass in a custom `BertConfig` to `from_pretrained`, and that’s where you would set those parameters: [BERT](https://huggingface.co/docs/transformers/v4.21.3/en/model_doc/bert#transformers.BertConfig) If you had other custom stuff that you needed to add to your model, maybe this would be useful? [Sharing custom models](https://huggingface.co/docs/transformers/custom_models) For your current model, I can’t unpickle the `pytorch_model.bin` file because it looks for your `BERTSentimentClassifier`, but since you’ve already trained the model maybe it’s possible for you to unpickle that locally, edit the state dict manually, and use that state dict on a model created with `BertForSequenceClassification.from_pretrained`? (I haven’t tried doing that myself before, so I don’t know how easy/possible it is.) ---
**Author:** ![SickBoy](https://avatars.discourse-cdn.com/v4/letter/s/7ea924/32.png) [@SickBoy](https://discuss.huggingface.co/u/SickBoy)\ **Post date:** [September 9, 2022, 2:24am UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/5 "2022-09-09T02:24:48Z")
Thanks @NimaBoscarino, I chose to do the training with the huggin face `trainer` and instantiating the model as `model = BertForSequenceClassification.from_pretrained(model_name, num_labels=n_classes)`as the tutorial shows and it worked. ---
**Author:** ![rvaila0424](https://avatars.discourse-cdn.com/v4/letter/r/f0a364/32.png) [@rvaila0424](https://discuss.huggingface.co/u/rvaila0424)\ **Post date:** [June 22, 2023, 10:40pm UTC](https://discuss.huggingface.co/t/how-to-load-a-torch-model-with-transformers/22699/6 "2023-06-22T22:40:37Z")
If the models are very similar, modifying the keys in the state\_dict is probably a quicker way to go! That’s what I did to load a locally fine-tuned `HubertForSequenceClassification` model into the HF’s `HubertForSequenceClassification` class.