Open WeiXuanLi-1024 opened 11 months ago
Does this tage_2 checkpoint weights your provide include Qformer part weights which PEFT from data {alpaca_gpt4_data.json and lava_instruct_150k.json } ? https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/alpacaLlava_llamaQformerv2Peft_13b
抱歉没太能够理解您的问题。[https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/alpacaLlava_llamaQformerv2Peft_13b]()是基于[https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/caption_llamaQformerv2_13b](),再在alpaca和llava上训练得到的,包含推断所需的所有参数
你们在训练stage_2的时候,训练出来两个权重 alpacaLlava_llamaQformerv2Peft_13b 和 alpacaLlava_llamaQformerv2_13b ,前者是部分PEFT,后者是全参数微调, 我想请教的是,在训练过程中,PEFT只有llama参与训练了吗?全参数微调Qformer 部分有参与更新吗?
目前,qfromer内部的参数在PEFT和全参数微调中都是没有被更新的、
Does this tage_2 checkpoint weights your provide include Qformer part weights which PEFT from data {alpaca_gpt4_data.json and lava_instruct_150k.json } ?
https://huggingface.co/Alpha-VLLM/LLaMA2-Accessory/tree/main/finetune/mm/alpacaLlava_llamaQformerv2Peft_13b