Open phellonchen opened 5 months ago
for j in range(8): cur_image_features = image_features[cur_image_idx+j*4] cur_new_input_embeds.append(cur_image_features) cur_new_labels.append(torch.full((cur_image_features.shape[0],), IGNORE_INDEX, device=cur_labels.device, dtype=cur_labels.dtype))
what is the meaning of '8' and '4'?
i got the same issue, if there's only one input image i then image_features shape is [8, 64, 5120], so cur_image_idx+j*4 will lead to out of bound
cur_image_idx+j*4
what is the meaning of '8' and '4'?