{ "metadata": { "total_size": 1516498944 }, "weight_map": { "embedder.0.auto_model.emb_ln.bias": "model-00006-of-00008.safetensors", "embedder.0.auto_model.emb_ln.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.embeddings.token_type_embeddings.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.embeddings.word_embeddings.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.attn.Wqkv.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.attn.out_proj.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.mlp.fc11.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.mlp.fc12.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.mlp.fc2.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.norm1.bias": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.norm1.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.norm2.bias": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.0.norm2.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.attn.Wqkv.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.attn.out_proj.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.mlp.fc11.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.mlp.fc12.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.mlp.fc2.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.norm1.bias": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.norm1.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.norm2.bias": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.1.norm2.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.attn.Wqkv.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.attn.out_proj.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.mlp.fc11.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.mlp.fc12.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.mlp.fc2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.norm1.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.norm1.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.norm2.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.10.norm2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.attn.Wqkv.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.attn.out_proj.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.mlp.fc11.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.mlp.fc12.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.mlp.fc2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.norm1.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.norm1.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.norm2.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.11.norm2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.attn.Wqkv.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.attn.out_proj.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.mlp.fc11.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.mlp.fc12.weight": "model-00006-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.2.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.attn.Wqkv.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.attn.out_proj.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.mlp.fc11.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.mlp.fc12.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.3.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.attn.Wqkv.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.attn.out_proj.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.mlp.fc11.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.mlp.fc12.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.4.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.attn.Wqkv.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.attn.out_proj.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.mlp.fc11.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.mlp.fc12.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.5.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.attn.Wqkv.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.attn.out_proj.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.mlp.fc11.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.mlp.fc12.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.6.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.attn.Wqkv.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.attn.out_proj.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.mlp.fc11.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.mlp.fc12.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.mlp.fc2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.norm1.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.norm1.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.norm2.bias": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.7.norm2.weight": "model-00007-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.attn.Wqkv.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.attn.out_proj.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.mlp.fc11.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.mlp.fc12.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.mlp.fc2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.norm1.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.norm1.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.norm2.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.8.norm2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.attn.Wqkv.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.attn.out_proj.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.mlp.fc11.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.mlp.fc12.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.mlp.fc2.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.norm1.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.norm1.weight": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.norm2.bias": "model-00008-of-00008.safetensors", "embedder.0.auto_model.encoder.layers.9.norm2.weight": "model-00008-of-00008.safetensors", "embedding_transform.0.bias": "model-00005-of-00008.safetensors", "embedding_transform.0.weight": "model-00005-of-00008.safetensors", "embedding_transform.3.bias": "model-00005-of-00008.safetensors", "embedding_transform.3.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "model-00004-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.decoder.final_layer_norm.weight": "model-00005-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors", "encoder_decoder.encoder.final_layer_norm.weight": "model-00003-of-00008.safetensors", "encoder_decoder.shared.weight": "model-00001-of-00008.safetensors" } }