Created
November 11, 2019 09:27
-
-
Save echan00/4154458473c4698c93d0597c617ff01a to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| encoder.version torch.Size([1]) | |
| encoder.embed_tokens.weight torch.Size([41104, 512]) | |
| encoder.embed_positions._float_tensor torch.Size([1]) | |
| encoder.layers.0.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.0.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.0.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.0.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.0.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.0.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.0.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.0.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.0.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.0.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.0.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.0.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.0.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.0.fc1.bias torch.Size([1024]) | |
| encoder.layers.0.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.0.fc2.bias torch.Size([512]) | |
| encoder.layers.0.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.0.final_layer_norm.bias torch.Size([512]) | |
| encoder.layers.1.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.1.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.1.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.1.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.1.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.1.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.1.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.1.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.1.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.1.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.1.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.1.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.1.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.1.fc1.bias torch.Size([1024]) | |
| encoder.layers.1.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.1.fc2.bias torch.Size([512]) | |
| encoder.layers.1.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.1.final_layer_norm.bias torch.Size([512]) | |
| encoder.layers.2.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.2.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.2.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.2.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.2.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.2.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.2.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.2.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.2.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.2.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.2.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.2.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.2.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.2.fc1.bias torch.Size([1024]) | |
| encoder.layers.2.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.2.fc2.bias torch.Size([512]) | |
| encoder.layers.2.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.2.final_layer_norm.bias torch.Size([512]) | |
| encoder.layers.3.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.3.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.3.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.3.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.3.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.3.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.3.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.3.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.3.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.3.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.3.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.3.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.3.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.3.fc1.bias torch.Size([1024]) | |
| encoder.layers.3.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.3.fc2.bias torch.Size([512]) | |
| encoder.layers.3.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.3.final_layer_norm.bias torch.Size([512]) | |
| encoder.layers.4.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.4.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.4.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.4.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.4.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.4.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.4.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.4.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.4.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.4.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.4.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.4.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.4.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.4.fc1.bias torch.Size([1024]) | |
| encoder.layers.4.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.4.fc2.bias torch.Size([512]) | |
| encoder.layers.4.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.4.final_layer_norm.bias torch.Size([512]) | |
| encoder.layers.5.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| encoder.layers.5.self_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.5.self_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.5.self_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.5.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| encoder.layers.5.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| encoder.layers.5.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| encoder.layers.5.bert_attn.in_proj_bias torch.Size([1536]) | |
| encoder.layers.5.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| encoder.layers.5.bert_attn.out_proj.bias torch.Size([512]) | |
| encoder.layers.5.self_attn_layer_norm.weight torch.Size([512]) | |
| encoder.layers.5.self_attn_layer_norm.bias torch.Size([512]) | |
| encoder.layers.5.fc1.weight torch.Size([1024, 512]) | |
| encoder.layers.5.fc1.bias torch.Size([1024]) | |
| encoder.layers.5.fc2.weight torch.Size([512, 1024]) | |
| encoder.layers.5.fc2.bias torch.Size([512]) | |
| encoder.layers.5.final_layer_norm.weight torch.Size([512]) | |
| encoder.layers.5.final_layer_norm.bias torch.Size([512]) | |
| decoder.version torch.Size([1]) | |
| decoder.embed_tokens.weight torch.Size([41104, 512]) | |
| decoder.embed_positions._float_tensor torch.Size([1]) | |
| decoder.layers.0.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.0.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.0.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.0.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.0.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.0.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.0.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.0.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.0.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.0.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.0.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.0.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.0.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.0.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.0.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.0.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.0.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.0.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.0.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.0.fc1.bias torch.Size([1024]) | |
| decoder.layers.0.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.0.fc2.bias torch.Size([512]) | |
| decoder.layers.0.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.0.final_layer_norm.bias torch.Size([512]) | |
| decoder.layers.1.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.1.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.1.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.1.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.1.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.1.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.1.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.1.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.1.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.1.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.1.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.1.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.1.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.1.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.1.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.1.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.1.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.1.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.1.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.1.fc1.bias torch.Size([1024]) | |
| decoder.layers.1.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.1.fc2.bias torch.Size([512]) | |
| decoder.layers.1.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.1.final_layer_norm.bias torch.Size([512]) | |
| decoder.layers.2.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.2.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.2.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.2.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.2.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.2.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.2.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.2.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.2.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.2.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.2.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.2.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.2.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.2.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.2.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.2.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.2.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.2.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.2.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.2.fc1.bias torch.Size([1024]) | |
| decoder.layers.2.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.2.fc2.bias torch.Size([512]) | |
| decoder.layers.2.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.2.final_layer_norm.bias torch.Size([512]) | |
| decoder.layers.3.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.3.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.3.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.3.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.3.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.3.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.3.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.3.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.3.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.3.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.3.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.3.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.3.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.3.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.3.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.3.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.3.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.3.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.3.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.3.fc1.bias torch.Size([1024]) | |
| decoder.layers.3.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.3.fc2.bias torch.Size([512]) | |
| decoder.layers.3.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.3.final_layer_norm.bias torch.Size([512]) | |
| decoder.layers.4.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.4.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.4.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.4.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.4.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.4.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.4.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.4.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.4.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.4.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.4.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.4.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.4.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.4.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.4.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.4.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.4.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.4.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.4.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.4.fc1.bias torch.Size([1024]) | |
| decoder.layers.4.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.4.fc2.bias torch.Size([512]) | |
| decoder.layers.4.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.4.final_layer_norm.bias torch.Size([512]) | |
| decoder.layers.5.self_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.5.self_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.5.self_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.5.self_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.5.self_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.5.self_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.5.encoder_attn.in_proj_weight torch.Size([1536, 512]) | |
| decoder.layers.5.encoder_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.5.encoder_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.5.encoder_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.5.bert_attn.k_proj_weight torch.Size([512, 768]) | |
| decoder.layers.5.bert_attn.v_proj_weight torch.Size([512, 768]) | |
| decoder.layers.5.bert_attn.q_proj_weight torch.Size([512, 512]) | |
| decoder.layers.5.bert_attn.in_proj_bias torch.Size([1536]) | |
| decoder.layers.5.bert_attn.out_proj.weight torch.Size([512, 512]) | |
| decoder.layers.5.bert_attn.out_proj.bias torch.Size([512]) | |
| decoder.layers.5.encoder_attn_layer_norm.weight torch.Size([512]) | |
| decoder.layers.5.encoder_attn_layer_norm.bias torch.Size([512]) | |
| decoder.layers.5.fc1.weight torch.Size([1024, 512]) | |
| decoder.layers.5.fc1.bias torch.Size([1024]) | |
| decoder.layers.5.fc2.weight torch.Size([512, 1024]) | |
| decoder.layers.5.fc2.bias torch.Size([512]) | |
| decoder.layers.5.final_layer_norm.weight torch.Size([512]) | |
| decoder.layers.5.final_layer_norm.bias torch.Size([512]) | |
| bert_encoder.embeddings.word_embeddings.weight torch.Size([119547, 768]) | |
| bert_encoder.embeddings.position_embeddings.weight torch.Size([512, 768]) | |
| bert_encoder.embeddings.token_type_embeddings.weight torch.Size([2, 768]) | |
| bert_encoder.embeddings.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.embeddings.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.0.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.0.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.0.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.0.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.0.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.0.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.0.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.0.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.0.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.0.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.1.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.1.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.1.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.1.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.1.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.1.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.1.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.1.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.1.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.1.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.2.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.2.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.2.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.2.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.2.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.2.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.2.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.2.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.2.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.2.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.3.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.3.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.3.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.3.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.3.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.3.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.3.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.3.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.3.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.3.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.4.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.4.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.4.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.4.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.4.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.4.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.4.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.4.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.4.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.4.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.5.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.5.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.5.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.5.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.5.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.5.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.5.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.5.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.5.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.5.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.6.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.6.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.6.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.6.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.6.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.6.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.6.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.6.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.6.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.6.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.7.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.7.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.7.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.7.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.7.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.7.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.7.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.7.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.7.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.7.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.8.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.8.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.8.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.8.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.8.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.8.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.8.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.8.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.8.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.8.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.9.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.9.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.9.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.9.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.9.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.9.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.9.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.9.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.9.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.9.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.10.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.10.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.10.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.10.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.10.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.10.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.10.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.10.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.10.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.10.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.self.query.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.11.attention.self.query.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.self.key.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.11.attention.self.key.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.self.value.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.11.attention.self.value.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.output.dense.weight torch.Size([768, 768]) | |
| bert_encoder.encoder.layer.11.attention.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.11.attention.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.intermediate.dense.weight torch.Size([3072, 768]) | |
| bert_encoder.encoder.layer.11.intermediate.dense.bias torch.Size([3072]) | |
| bert_encoder.encoder.layer.11.output.dense.weight torch.Size([768, 3072]) | |
| bert_encoder.encoder.layer.11.output.dense.bias torch.Size([768]) | |
| bert_encoder.encoder.layer.11.output.LayerNorm.weight torch.Size([768]) | |
| bert_encoder.encoder.layer.11.output.LayerNorm.bias torch.Size([768]) | |
| bert_encoder.pooler.dense.weight torch.Size([768, 768]) | |
| bert_encoder.pooler.dense.bias torch.Size([768]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment