I encountered a warning #29
Description
Instantiating LlamaAttention without passing layer_idx is not recommended and will to errors during the forward call, if caching is used. Please make sure to provide a layer_idx when creating this class.
Loading checkpoint shards: 100%|██████████| 33/33 [00:22<00:00, 1.47it/s]
Some weights of MPLUGOwl2LlamaForCausalLM were not initialized from the model checkpoint at D:\桌面\mplug_owl2_7b_448_qinstruct_preview_v0.1 and are newly initialized: ['model.visual_abstractor.encoder.layers.4.crossattention.attention.k_pos_embed', 'model.visual_abstractor.encoder.layers.0.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.5.crossattention.attention.k_pos_embed', 'model.visual_abstractor.encoder.layers.5.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.2.crossattention.attention.k_pos_embed', 'model.visual_abstractor.encoder.layers.1.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.3.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.4.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.0.crossattention.attention.k_pos_embed', 'model.visual_abstractor.encoder.layers.2.crossattention.attention.q_pos_embed', 'model.visual_abstractor.encoder.layers.3.crossattention.attention.k_pos_embed', 'model.visual_abstractor.encoder.layers.1.crossattention.attention.k_pos_embed']
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
WARNING:root:Some parameters are on the meta device device because they were offloaded to the cpu.
Evaluating [E:\Project\Q-Align-main\playground\data\test_jsons\AGIQA-3K.json]: 100%|██████████| 2982/2982 [24:42<00:00, 2.01it/s]