lexilii

The article mentions that the length of the training samples is 60. However, in the provided inference script, the length used is 100. So I'm confused.

load_state_dict: _IncompatibleKeys(missing_keys=[], unexpected_keys=['temp', 'itm_head.weight', 'itm_head.bias'])

1

运行 InternVideo2_stage2_1B 的 demo.ipynb 时，intern_model, tokenizer = setup_internvideo2(config) 会报如下警告： load_state_dict: _IncompatibleKeys(missing_keys=[], unexpected_keys=['temp', 'itm_head.weight', 'itm_head.bias']) 最终能够得到如下运行结果： text: A man in a gray sweater plays fetch with his dog in the snowy...