| { | |
| "metadata": { | |
| "total_size": 1370288640 | |
| }, | |
| "weight_map": { | |
| "embedder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.0.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.1.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.10.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.10.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.11.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.2.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.3.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.4.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.5.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.6.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.7.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.8.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.block.9.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin", | |
| "embedder.embed_tokens.weight": "pytorch_model-00006-of-00008.bin", | |
| "embedder.final_layer_norm.weight": "pytorch_model-00008-of-00008.bin", | |
| "embedding_transform.0.bias": "pytorch_model-00005-of-00008.bin", | |
| "embedding_transform.0.weight": "pytorch_model-00005-of-00008.bin", | |
| "embedding_transform.3.bias": "pytorch_model-00005-of-00008.bin", | |
| "embedding_transform.3.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.decoder.embed_tokens.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.decoder.final_layer_norm.weight": "pytorch_model-00005-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin", | |
| "encoder_decoder.encoder.embed_tokens.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.encoder.final_layer_norm.weight": "pytorch_model-00003-of-00008.bin", | |
| "encoder_decoder.lm_head.weight": "pytorch_model-00001-of-00008.bin", | |
| "encoder_decoder.shared.weight": "pytorch_model-00001-of-00008.bin" | |
| } | |
| } | |