Have you guys used llama 3.2 for sentiment classification and get “weights are not completely loaded” warning. As I understand, forte of llama 3.2 is text completion but I wanted to see if any one is using “sentiment-analysis” and what are the best practices for that.
1 Like
hi @datashovel
Yes it’s same here:
Some weights of LlamaForSequenceClassification were not initialized from the model checkpoint at meta-llama/Llama-3.2-1B and are newly initialized: ['score.weight']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
I guess you can fine-tune it as described:
I hope you can find a useful dataset here:
1 Like