small3 / pytorch_model.bin.index.json
Narsil's picture
Narsil HF staff
Small2 but sharded.
07a3942 unverified
raw
history blame
3.55 kB
{
"metadata": {
"total_size": 240732
},
"weight_map": {
"bert.embeddings.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
"bert.embeddings.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
"bert.embeddings.position_embeddings.weight": "pytorch_model-00003-of-00003.bin",
"bert.embeddings.position_ids": "pytorch_model-00001-of-00003.bin",
"bert.embeddings.token_type_embeddings.weight": "pytorch_model-00003-of-00003.bin",
"bert.embeddings.word_embeddings.weight": "pytorch_model-00002-of-00003.bin",
"bert.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.output.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.0.output.dense.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.key.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.key.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.query.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.query.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.value.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.attention.self.value.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.output.dense.bias": "pytorch_model-00003-of-00003.bin",
"bert.encoder.layer.1.output.dense.weight": "pytorch_model-00003-of-00003.bin",
"classifier.bias": "pytorch_model-00003-of-00003.bin",
"classifier.weight": "pytorch_model-00003-of-00003.bin"
}
}