{ "metadata": { "total_size": 12636006400 }, "weight_map": { "language_model.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.14.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.15.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.16.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.17.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.18.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors", "language_model.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "language_model.encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "language_model.encoder.final_layer_norm.weight": "model-00002-of-00003.safetensors", "language_model.lm_head.weight": "model-00003-of-00003.safetensors", "language_model.shared.weight": "model-00001-of-00003.safetensors", "language_projection.bias": "model-00001-of-00003.safetensors", "language_projection.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.0.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.1.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.10.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.11.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.2.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.3.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.4.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.5.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.6.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.7.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.crossattention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.8.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.key.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.key.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.query.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.query.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.value.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.attention.value.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.output.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.output.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.intermediate_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.intermediate_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.output_query.LayerNorm.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.output_query.LayerNorm.weight": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.output_query.dense.bias": "model-00001-of-00003.safetensors", "qformer.encoder.layer.9.output_query.dense.weight": "model-00001-of-00003.safetensors", "qformer.layernorm.bias": "model-00001-of-00003.safetensors", "qformer.layernorm.weight": "model-00001-of-00003.safetensors", "query_tokens": "model-00001-of-00003.safetensors", "vision_model.embeddings.cls_token": "model-00001-of-00003.safetensors", "vision_model.embeddings.distillation_token": "model-00001-of-00003.safetensors", "vision_model.embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors", "vision_model.embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors", "vision_model.embeddings.position_embeddings": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.0.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.1.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.10.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.11.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.2.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.3.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.4.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.5.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.6.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.7.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.8.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.key.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.key.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.query.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.query.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.value.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.attention.value.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.attention.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.intermediate.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.intermediate.dense.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.layernorm_after.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.layernorm_after.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.layernorm_before.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.layernorm_before.weight": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.output.dense.bias": "model-00001-of-00003.safetensors", "vision_model.encoder.layer.9.output.dense.weight": "model-00001-of-00003.safetensors", "vision_model.layernorm.bias": "model-00001-of-00003.safetensors", "vision_model.layernorm.weight": "model-00001-of-00003.safetensors", "vision_model.pooler.dense.bias": "model-00001-of-00003.safetensors", "vision_model.pooler.dense.weight": "model-00001-of-00003.safetensors" } }