Open zeroQiaoba opened 3 months ago
In Video-LLaMA, we notice that you load LlamaForCausalLM from ./models/modelling_llama.py. I wonder why not directly load it by "from transformers import LlamaForCausalLM". Do you make any change of the original code in Transforms packages?
I was wondering this same thing, any clarification here?
In Video-LLaMA, we notice that you load LlamaForCausalLM from ./models/modelling_llama.py. I wonder why not directly load it by "from transformers import LlamaForCausalLM". Do you make any change of the original code in Transforms packages?