# Text Classification models give "you should probably train your model" **URL:** \ **Category:** Beginners\ **Created:** [March 27, 2024, 4:00pm UTC](https://discuss.huggingface.co/t/text-classification-models-give-you-should-probably-train-your-model/78962 "2024-03-27T16:00:25Z")\ **Posts on this page:** 1\ **Page:** 1
**Author:** ![bdzyubak](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/bdzyubak/32/27644_2.png) [@bdzyubak](https://discuss.huggingface.co/u/bdzyubak)\ **Post date:** [March 27, 2024, 4:00pm UTC](https://discuss.huggingface.co/t/text-classification-models-give-you-should-probably-train-your-model/78962/1 "2024-03-27T16:00:25Z")
I tried using a few of the top downloaded transformer models for text classification [SamLowe/roberta-base-go\_emotions · Hugging Face](https://huggingface.co/SamLowe/roberta-base-go_emotions), [ProsusAI/finbert · Hugging Face](https://huggingface.co/ProsusAI/finbert?text=Stocks+rallied+and+the+British+pound+gained). The pages seems to imply it should work out of the box to yield sentiment given a sentence. However, I get a warning saying: > If you want to use `RobertaLMHeadModel` as a standalone, add `is_decoder=True.` > Some weights of RobertaForCausalLM were not initialized from the model checkpoint at SamLowe/roberta-base-go\_emotions and are newly initialized: [‘lm\_head.bias’, ‘lm\_head.decoder.bias’, ‘lm\_head.dense.bias’, ‘lm\_head.dense.weight’, ‘lm\_head.layer\_norm.bias’, ‘lm\_head.layer\_norm.weight’] > You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. Using pipeline(“text-generation”, model=“SamLowe/roberta-base-go\_emotions”, top\_k=None, is\_decoder=True) throws unrecognized kwarg. If I try to use it as is, it appends characters to input text rather than trying to classify sentiment. Am I using this model wrong? Thanks much