model.safetensors.index.json

{
  "metadata": {
    "total_size": 2908701696
  },
  "weight_map": {
    "embedder.embeddings.LayerNorm.bias": "model-00010-of-00010.safetensors",
    "embedder.embeddings.LayerNorm.weight": "model-00010-of-00010.safetensors",
    "embedder.embeddings.position_embeddings.weight": "model-00010-of-00010.safetensors",
    "embedder.embeddings.word_embeddings.weight": "model-00009-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.0.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.1.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.2.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.3.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.4.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.k_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.k_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.out_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.out_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.q_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.q_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.v_lin.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.attention.v_lin.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.ffn.lin1.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.ffn.lin1.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.ffn.lin2.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.ffn.lin2.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.output_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.output_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
    "embedder.transformer.layer.5.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
    "embedding_transform.0.bias": "model-00008-of-00010.safetensors",
    "embedding_transform.0.weight": "model-00008-of-00010.safetensors",
    "embedding_transform.3.bias": "model-00008-of-00010.safetensors",
    "embedding_transform.3.weight": "model-00008-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
    "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
    "encoder_decoder.decoder.final_layer_norm.weight": "model-00006-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.encoder.final_layer_norm.weight": "model-00003-of-00010.safetensors",
    "encoder_decoder.lm_head.weight": "model-00007-of-00010.safetensors",
    "encoder_decoder.shared.weight": "model-00001-of-00010.safetensors"
  }
}