YifeiWang
YifeiWang
In LlamaModeling.py, the LlamaRMSNorm function outputs the weights * scaled hidden_states like below  **RMSNormPre definition in Transformer_lens: it seems that this function just outputs the scaled hidden_states**  **The...
I download COCO 2017 dataset from huggingface (a repo named phiyodr/coco2017) and the structures of data is different . I wonder where the coco 2027 is downloaded?