754563116

> #25 感谢大佬，正解，解决了 你好，请问你的解决了吗？ 我按照上面那个人的方法，又出现一个新的错误：state_dict[new_key] = state_dict.pop(old_key) kyError: 'cls.predictions.transform.LayerNorm.gamma'

按照你的方法出现了新的错误，我在你的基础上又改了改，代码如下： state_dict = torch.load(path, map_location='cpu') old_keys = [] new_keys = [] for key in list(state_dict.keys()): # print(key) new_key = None if 'gamma' in key: new_key = key.replace('gamma', 'weight') if 'beta'...

> 我是这样处理的： state_dict = torch.load(args.init_checkpoint, map_location='cpu') new_keys = ["embeddings.word_embeddings.weight", "embeddings.position_embeddings.weight", "embeddings.token_type_embeddings.weight", "embeddings.LayerNorm.gamma", "embeddings.LayerNorm.beta", "encoder.layer.0.attention.self.query.weight", "encoder.layer.0.attention.self.query.bias", "encoder.layer.0.attention.self.key.weight", "encoder.layer.0.attention.self.key.bias", "encoder.layer.0.attention.self.value.weight", "encoder.layer.0.attention.self.value.bias", "encoder.layer.0.attention.output.dense.weight", "encoder.layer.0.attention.output.dense.bias", "encoder.layer.0.attention.output.LayerNorm.gamma", "encoder.layer.0.attention.output.LayerNorm.beta", "encoder.layer.0.intermediate.dense.weight", "encoder.layer.0.intermediate.dense.bias", "encoder.layer.0.output.dense.weight", "encoder.layer.0.output.dense.bias", "encoder.layer.0.output.LayerNorm.gamma", "encoder.layer.0.output.LayerNorm.beta", "encoder.layer.1.attention.self.query.weight",...

我也是同样的错误

> the same errors, is there anyone know the way to fix this error? thanks > > ================================================================= > RuntimeError: Error(s) in loading state_dict for BertModel: > Missing key(s) in...