| { | |
| "metadata": { | |
| "total_size": 3481939968 | |
| }, | |
| "weight_map": { | |
| "embedder.embeddings.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.embeddings.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.embeddings.position_embeddings.weight": "model-00010-of-00011.safetensors", | |
| "embedder.embeddings.token_type_embeddings.weight": "model-00010-of-00011.safetensors", | |
| "embedder.embeddings.word_embeddings.weight": "model-00009-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.0.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.1.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.key.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.key.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.query.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.query.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.value.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.attention.self.value.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.intermediate.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.intermediate.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.10.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.key.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.key.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.query.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.query.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.value.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.attention.self.value.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.intermediate.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.intermediate.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.11.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.2.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.3.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.4.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.5.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.output.LayerNorm.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.output.LayerNorm.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.output.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.output.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.key.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.key.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.query.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.query.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.value.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.attention.self.value.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.intermediate.dense.bias": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.intermediate.dense.weight": "model-00010-of-00011.safetensors", | |
| "embedder.encoder.layer.6.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.6.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.6.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.6.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.key.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.key.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.query.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.query.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.value.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.attention.self.value.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.intermediate.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.intermediate.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.7.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.key.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.key.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.query.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.query.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.value.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.attention.self.value.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.intermediate.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.intermediate.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.8.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.key.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.key.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.query.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.query.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.value.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.attention.self.value.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.intermediate.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.intermediate.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.output.LayerNorm.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.output.LayerNorm.weight": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.output.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.encoder.layer.9.output.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedder.pooler.dense.bias": "model-00011-of-00011.safetensors", | |
| "embedder.pooler.dense.weight": "model-00011-of-00011.safetensors", | |
| "embedding_transform.0.bias": "model-00008-of-00011.safetensors", | |
| "embedding_transform.0.weight": "model-00008-of-00011.safetensors", | |
| "embedding_transform.3.bias": "model-00008-of-00011.safetensors", | |
| "embedding_transform.3.weight": "model-00008-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "model-00005-of-00011.safetensors", | |
| "encoder_decoder.decoder.final_layer_norm.weight": "model-00006-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.encoder.final_layer_norm.weight": "model-00003-of-00011.safetensors", | |
| "encoder_decoder.lm_head.weight": "model-00007-of-00011.safetensors", | |
| "encoder_decoder.shared.weight": "model-00001-of-00011.safetensors" | |
| } | |
| } | |