Closed yzbx closed 7 months ago
I use the weight from internlm-xcomposer2-vl-7b. The evaluation code warning when loading the model.
weights of ['vit.vision_tower.vision_model_post_layernorm.weight', 'vit.vision_tower.vision_model.post_layernorm.bias'] are newly initialized
is this the reason for the poor performance in mmbench-dev-cn?
please note the code internlm-xcomposer2-vl-7b/build_mlp.py in modelscope is different from internlm-xcomposer2-vl-7b/build_mlp.py in huggingface
class CLIPVisionTower(nn.Module): def __init__(self, vision_tower): super().__init__() self.is_loaded = False self.is_resize_pos = False from modelscope import snapshot_download self.vision_tower_name = snapshot_download("AI-ModelScope/clip-vit-large-patch14-336") ### different self.select_layer = -1 self.select_feature = 'patch' self.load_model() self.resize_pos()
use the code from branch InternLM-XComposer2 instead of main fix the problem, after fix the import library bug in code, the acc is matched.
I use the weight from internlm-xcomposer2-vl-7b. The evaluation code warning when loading the model.
is this the reason for the poor performance in mmbench-dev-cn?
please note the code internlm-xcomposer2-vl-7b/build_mlp.py in modelscope is different from internlm-xcomposer2-vl-7b/build_mlp.py in huggingface