PaddlePaddle-Longformer-model-base-4096

PyTorch Shape Paddle Shape
embeddings.word_embeddings.weight [50265, 768] embeddings.word_embeddings.weight
embeddings.position_embeddings.weight [4098, 768] embeddings.position_embeddings.weight
embeddings.token_type_embeddings.weight [1, 768] embeddings.token_type_embeddings.weight
embeddings.LayerNorm.weight [768] embeddings.layer_norm.weight
embeddings.LayerNorm.bias [768] embeddings.layer_norm.bias
encoder.layer.0.attention.self.query.weight [768, 768] encoder.layers.0.self_attn.query.weight T
encoder.layer.0.attention.self.query.bias [768] encoder.layers.0.self_attn.query.bias
encoder.layer.0.attention.self.key.weight [768, 768] encoder.layers.0.self_attn.key.weight T
encoder.layer.0.attention.self.key.bias [768] encoder.layers.0.self_attn.key.bias
encoder.layer.0.attention.self.value.weight [768, 768] encoder.layers.0.self_attn.value.weight T
encoder.layer.0.attention.self.value.bias [768] encoder.layers.0.self_attn.value.bias
encoder.layer.0.attention.self.query_global.weight [768, 768] encoder.layers.0.self_attn.query_global.weight T
encoder.layer.0.attention.self.query_global.bias [768] encoder.layers.0.self_attn.query_global.bias
encoder.layer.0.attention.self.key_global.weight [768, 768] encoder.layers.0.self_attn.key_global.weight T
encoder.layer.0.attention.self.key_global.bias [768] encoder.layers.0.self_attn.key_global.bias
encoder.layer.0.attention.self.value_global.weight [768, 768] encoder.layers.0.self_attn.value_global.weight T
encoder.layer.0.attention.self.value_global.bias [768] encoder.layers.0.self_attn.value_global.bias
encoder.layer.0.attention.output.dense.weight [768, 768] encoder.layers.0.self_attn.out.weight T
encoder.layer.0.attention.output.dense.bias [768] encoder.layers.0.self_attn.out.bias
encoder.layer.0.attention.output.LayerNorm.weight [768] encoder.layers.0.norm1.weight
encoder.layer.0.attention.output.LayerNorm.bias [768] encoder.layers.0.norm1.bias
encoder.layer.0.intermediate.dense.weight [3072, 768] encoder.layers.0.linear1.weight T [768, 3072]
encoder.layer.0.intermediate.dense.bias [3072] encoder.layers.0.linear1.bias
encoder.layer.0.output.dense.weight [768, 3072] encoder.layers.0.linear2.weight T [3072, 768]
encoder.layer.0.output.dense.bias [768] encoder.layers.0.linear2.bias
encoder.layer.0.output.LayerNorm.weight [768] encoder.layers.0.norm2.weight
encoder.layer.0.output.LayerNorm.bias [768] encoder.layers.0.norm2.bias
pooler.dense.weight [768, 768] pooler.dense.weight T
pooler.dense.bias [768] pooler.dense.bias
In [1]:
from transformers import LongformerModel
In [2]:
model = LongformerModel.from_pretrained("allenai/longformer-base-4096")
state_dict = model.state_dict().keys()
Some weights of the model checkpoint at allenai/longformer-base-4096 were not used when initializing LongformerModel: ['lm_head.dense.weight', 'lm_head.layer_norm.bias', 'lm_head.dense.bias', 'lm_head.bias', 'lm_head.decoder.weight', 'lm_head.layer_norm.weight']
- This IS expected if you are initializing LongformerModel from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
- This IS NOT expected if you are initializing LongformerModel from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
In [3]:
state_dict
Out[3]:
odict_keys(['embeddings.position_ids', 'embeddings.word_embeddings.weight', 'embeddings.position_embeddings.weight', 'embeddings.token_type_embeddings.weight', 'embeddings.LayerNorm.weight', 'embeddings.LayerNorm.bias', '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.self.query_global.weight', 'encoder.layer.0.attention.self.query_global.bias', 'encoder.layer.0.attention.self.key_global.weight', 'encoder.layer.0.attention.self.key_global.bias', 'encoder.layer.0.attention.self.value_global.weight', 'encoder.layer.0.attention.self.value_global.bias', 'encoder.layer.0.attention.output.dense.weight', 'encoder.layer.0.attention.output.dense.bias', 'encoder.layer.0.attention.output.LayerNorm.weight', 'encoder.layer.0.attention.output.LayerNorm.bias', '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.weight', 'encoder.layer.0.output.LayerNorm.bias', 'encoder.layer.1.attention.self.query.weight', 'encoder.layer.1.attention.self.query.bias', 'encoder.layer.1.attention.self.key.weight', 'encoder.layer.1.attention.self.key.bias', 'encoder.layer.1.attention.self.value.weight', 'encoder.layer.1.attention.self.value.bias', 'encoder.layer.1.attention.self.query_global.weight', 'encoder.layer.1.attention.self.query_global.bias', 'encoder.layer.1.attention.self.key_global.weight', 'encoder.layer.1.attention.self.key_global.bias', 'encoder.layer.1.attention.self.value_global.weight', 'encoder.layer.1.attention.self.value_global.bias', 'encoder.layer.1.attention.output.dense.weight', 'encoder.layer.1.attention.output.dense.bias', 'encoder.layer.1.attention.output.LayerNorm.weight', 'encoder.layer.1.attention.output.LayerNorm.bias', 'encoder.layer.1.intermediate.dense.weight', 'encoder.layer.1.intermediate.dense.bias', 'encoder.layer.1.output.dense.weight', 'encoder.layer.1.output.dense.bias', 'encoder.layer.1.output.LayerNorm.weight', 'encoder.layer.1.output.LayerNorm.bias', 'encoder.layer.2.attention.self.query.weight', 'encoder.layer.2.attention.self.query.bias', 'encoder.layer.2.attention.self.key.weight', 'encoder.layer.2.attention.self.key.bias', 'encoder.layer.2.attention.self.value.weight', 'encoder.layer.2.attention.self.value.bias', 'encoder.layer.2.attention.self.query_global.weight', 'encoder.layer.2.attention.self.query_global.bias', 'encoder.layer.2.attention.self.key_global.weight', 'encoder.layer.2.attention.self.key_global.bias', 'encoder.layer.2.attention.self.value_global.weight', 'encoder.layer.2.attention.self.value_global.bias', 'encoder.layer.2.attention.output.dense.weight', 'encoder.layer.2.attention.output.dense.bias', 'encoder.layer.2.attention.output.LayerNorm.weight', 'encoder.layer.2.attention.output.LayerNorm.bias', 'encoder.layer.2.intermediate.dense.weight', 'encoder.layer.2.intermediate.dense.bias', 'encoder.layer.2.output.dense.weight', 'encoder.layer.2.output.dense.bias', 'encoder.layer.2.output.LayerNorm.weight', 'encoder.layer.2.output.LayerNorm.bias', 'encoder.layer.3.attention.self.query.weight', 'encoder.layer.3.attention.self.query.bias', 'encoder.layer.3.attention.self.key.weight', 'encoder.layer.3.attention.self.key.bias', 'encoder.layer.3.attention.self.value.weight', 'encoder.layer.3.attention.self.value.bias', 'encoder.layer.3.attention.self.query_global.weight', 'encoder.layer.3.attention.self.query_global.bias', 'encoder.layer.3.attention.self.key_global.weight', 'encoder.layer.3.attention.self.key_global.bias', 'encoder.layer.3.attention.self.value_global.weight', 'encoder.layer.3.attention.self.value_global.bias', 'encoder.layer.3.attention.output.dense.weight', 'encoder.layer.3.attention.output.dense.bias', 'encoder.layer.3.attention.output.LayerNorm.weight', 'encoder.layer.3.attention.output.LayerNorm.bias', 'encoder.layer.3.intermediate.dense.weight', 'encoder.layer.3.intermediate.dense.bias', 'encoder.layer.3.output.dense.weight', 'encoder.layer.3.output.dense.bias', 'encoder.layer.3.output.LayerNorm.weight', 'encoder.layer.3.output.LayerNorm.bias', 'encoder.layer.4.attention.self.query.weight', 'encoder.layer.4.attention.self.query.bias', 'encoder.layer.4.attention.self.key.weight', 'encoder.layer.4.attention.self.key.bias', 'encoder.layer.4.attention.self.value.weight', 'encoder.layer.4.attention.self.value.bias', 'encoder.layer.4.attention.self.query_global.weight', 'encoder.layer.4.attention.self.query_global.bias', 'encoder.layer.4.attention.self.key_global.weight', 'encoder.layer.4.attention.self.key_global.bias', 'encoder.layer.4.attention.self.value_global.weight', 'encoder.layer.4.attention.self.value_global.bias', 'encoder.layer.4.attention.output.dense.weight', 'encoder.layer.4.attention.output.dense.bias', 'encoder.layer.4.attention.output.LayerNorm.weight', 'encoder.layer.4.attention.output.LayerNorm.bias', 'encoder.layer.4.intermediate.dense.weight', 'encoder.layer.4.intermediate.dense.bias', 'encoder.layer.4.output.dense.weight', 'encoder.layer.4.output.dense.bias', 'encoder.layer.4.output.LayerNorm.weight', 'encoder.layer.4.output.LayerNorm.bias', 'encoder.layer.5.attention.self.query.weight', 'encoder.layer.5.attention.self.query.bias', 'encoder.layer.5.attention.self.key.weight', 'encoder.layer.5.attention.self.key.bias', 'encoder.layer.5.attention.self.value.weight', 'encoder.layer.5.attention.self.value.bias', 'encoder.layer.5.attention.self.query_global.weight', 'encoder.layer.5.attention.self.query_global.bias', 'encoder.layer.5.attention.self.key_global.weight', 'encoder.layer.5.attention.self.key_global.bias', 'encoder.layer.5.attention.self.value_global.weight', 'encoder.layer.5.attention.self.value_global.bias', 'encoder.layer.5.attention.output.dense.weight', 'encoder.layer.5.attention.output.dense.bias', 'encoder.layer.5.attention.output.LayerNorm.weight', 'encoder.layer.5.attention.output.LayerNorm.bias', 'encoder.layer.5.intermediate.dense.weight', 'encoder.layer.5.intermediate.dense.bias', 'encoder.layer.5.output.dense.weight', 'encoder.layer.5.output.dense.bias', 'encoder.layer.5.output.LayerNorm.weight', 'encoder.layer.5.output.LayerNorm.bias', 'encoder.layer.6.attention.self.query.weight', 'encoder.layer.6.attention.self.query.bias', 'encoder.layer.6.attention.self.key.weight', 'encoder.layer.6.attention.self.key.bias', 'encoder.layer.6.attention.self.value.weight', 'encoder.layer.6.attention.self.value.bias', 'encoder.layer.6.attention.self.query_global.weight', 'encoder.layer.6.attention.self.query_global.bias', 'encoder.layer.6.attention.self.key_global.weight', 'encoder.layer.6.attention.self.key_global.bias', 'encoder.layer.6.attention.self.value_global.weight', 'encoder.layer.6.attention.self.value_global.bias', 'encoder.layer.6.attention.output.dense.weight', 'encoder.layer.6.attention.output.dense.bias', 'encoder.layer.6.attention.output.LayerNorm.weight', 'encoder.layer.6.attention.output.LayerNorm.bias', 'encoder.layer.6.intermediate.dense.weight', 'encoder.layer.6.intermediate.dense.bias', 'encoder.layer.6.output.dense.weight', 'encoder.layer.6.output.dense.bias', 'encoder.layer.6.output.LayerNorm.weight', 'encoder.layer.6.output.LayerNorm.bias', 'encoder.layer.7.attention.self.query.weight', 'encoder.layer.7.attention.self.query.bias', 'encoder.layer.7.attention.self.key.weight', 'encoder.layer.7.attention.self.key.bias', 'encoder.layer.7.attention.self.value.weight', 'encoder.layer.7.attention.self.value.bias', 'encoder.layer.7.attention.self.query_global.weight', 'encoder.layer.7.attention.self.query_global.bias', 'encoder.layer.7.attention.self.key_global.weight', 'encoder.layer.7.attention.self.key_global.bias', 'encoder.layer.7.attention.self.value_global.weight', 'encoder.layer.7.attention.self.value_global.bias', 'encoder.layer.7.attention.output.dense.weight', 'encoder.layer.7.attention.output.dense.bias', 'encoder.layer.7.attention.output.LayerNorm.weight', 'encoder.layer.7.attention.output.LayerNorm.bias', 'encoder.layer.7.intermediate.dense.weight', 'encoder.layer.7.intermediate.dense.bias', 'encoder.layer.7.output.dense.weight', 'encoder.layer.7.output.dense.bias', 'encoder.layer.7.output.LayerNorm.weight', 'encoder.layer.7.output.LayerNorm.bias', 'encoder.layer.8.attention.self.query.weight', 'encoder.layer.8.attention.self.query.bias', 'encoder.layer.8.attention.self.key.weight', 'encoder.layer.8.attention.self.key.bias', 'encoder.layer.8.attention.self.value.weight', 'encoder.layer.8.attention.self.value.bias', 'encoder.layer.8.attention.self.query_global.weight', 'encoder.layer.8.attention.self.query_global.bias', 'encoder.layer.8.attention.self.key_global.weight', 'encoder.layer.8.attention.self.key_global.bias', 'encoder.layer.8.attention.self.value_global.weight', 'encoder.layer.8.attention.self.value_global.bias', 'encoder.layer.8.attention.output.dense.weight', 'encoder.layer.8.attention.output.dense.bias', 'encoder.layer.8.attention.output.LayerNorm.weight', 'encoder.layer.8.attention.output.LayerNorm.bias', 'encoder.layer.8.intermediate.dense.weight', 'encoder.layer.8.intermediate.dense.bias', 'encoder.layer.8.output.dense.weight', 'encoder.layer.8.output.dense.bias', 'encoder.layer.8.output.LayerNorm.weight', 'encoder.layer.8.output.LayerNorm.bias', 'encoder.layer.9.attention.self.query.weight', 'encoder.layer.9.attention.self.query.bias', 'encoder.layer.9.attention.self.key.weight', 'encoder.layer.9.attention.self.key.bias', 'encoder.layer.9.attention.self.value.weight', 'encoder.layer.9.attention.self.value.bias', 'encoder.layer.9.attention.self.query_global.weight', 'encoder.layer.9.attention.self.query_global.bias', 'encoder.layer.9.attention.self.key_global.weight', 'encoder.layer.9.attention.self.key_global.bias', 'encoder.layer.9.attention.self.value_global.weight', 'encoder.layer.9.attention.self.value_global.bias', 'encoder.layer.9.attention.output.dense.weight', 'encoder.layer.9.attention.output.dense.bias', 'encoder.layer.9.attention.output.LayerNorm.weight', 'encoder.layer.9.attention.output.LayerNorm.bias', 'encoder.layer.9.intermediate.dense.weight', 'encoder.layer.9.intermediate.dense.bias', 'encoder.layer.9.output.dense.weight', 'encoder.layer.9.output.dense.bias', 'encoder.layer.9.output.LayerNorm.weight', 'encoder.layer.9.output.LayerNorm.bias', 'encoder.layer.10.attention.self.query.weight', 'encoder.layer.10.attention.self.query.bias', 'encoder.layer.10.attention.self.key.weight', 'encoder.layer.10.attention.self.key.bias', 'encoder.layer.10.attention.self.value.weight', 'encoder.layer.10.attention.self.value.bias', 'encoder.layer.10.attention.self.query_global.weight', 'encoder.layer.10.attention.self.query_global.bias', 'encoder.layer.10.attention.self.key_global.weight', 'encoder.layer.10.attention.self.key_global.bias', 'encoder.layer.10.attention.self.value_global.weight', 'encoder.layer.10.attention.self.value_global.bias', 'encoder.layer.10.attention.output.dense.weight', 'encoder.layer.10.attention.output.dense.bias', 'encoder.layer.10.attention.output.LayerNorm.weight', 'encoder.layer.10.attention.output.LayerNorm.bias', 'encoder.layer.10.intermediate.dense.weight', 'encoder.layer.10.intermediate.dense.bias', 'encoder.layer.10.output.dense.weight', 'encoder.layer.10.output.dense.bias', 'encoder.layer.10.output.LayerNorm.weight', 'encoder.layer.10.output.LayerNorm.bias', 'encoder.layer.11.attention.self.query.weight', 'encoder.layer.11.attention.self.query.bias', 'encoder.layer.11.attention.self.key.weight', 'encoder.layer.11.attention.self.key.bias', 'encoder.layer.11.attention.self.value.weight', 'encoder.layer.11.attention.self.value.bias', 'encoder.layer.11.attention.self.query_global.weight', 'encoder.layer.11.attention.self.query_global.bias', 'encoder.layer.11.attention.self.key_global.weight', 'encoder.layer.11.attention.self.key_global.bias', 'encoder.layer.11.attention.self.value_global.weight', 'encoder.layer.11.attention.self.value_global.bias', 'encoder.layer.11.attention.output.dense.weight', 'encoder.layer.11.attention.output.dense.bias', 'encoder.layer.11.attention.output.LayerNorm.weight', 'encoder.layer.11.attention.output.LayerNorm.bias', 'encoder.layer.11.intermediate.dense.weight', 'encoder.layer.11.intermediate.dense.bias', 'encoder.layer.11.output.dense.weight', 'encoder.layer.11.output.dense.bias', 'encoder.layer.11.output.LayerNorm.weight', 'encoder.layer.11.output.LayerNorm.bias', 'pooler.dense.weight', 'pooler.dense.bias'])
In [ ]:
 

Comments