{ "metadata": { "total_size": 11705748448 }, "weight_map": { "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.18.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.19.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors", "decoder.block.23.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors", "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors", "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors", "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors", "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors", "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.final_layer_norm.weight": "model-00001-of-00003.safetensors", "encoder.mm_projector.bias": "model-00002-of-00003.safetensors", "encoder.mm_projector.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.embeddings.norm.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.embeddings.norm.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.downsample.norm.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.downsample.norm.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.0.downsample.reduction.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.downsample.norm.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.downsample.norm.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.1.downsample.reduction.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.0.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.1.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.10.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.11.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.12.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.13.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.2.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.3.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.4.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.5.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.intermediate.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.intermediate.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.6.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.output.dense.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.output.dense.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.key.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.key.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.query.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.query.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.relative_position_bias_table": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.relative_position_index": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.value.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.attention.self.value.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.layernorm_after.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.layernorm_after.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.layernorm_before.bias": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.layernorm_before.weight": "model-00001-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.7.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.8.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.blocks.9.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.downsample.norm.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.downsample.norm.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.2.downsample.reduction.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.0.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.output.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.key.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.key.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.query.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.query.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.relative_position_bias_table": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.relative_position_index": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.value.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.attention.self.value.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.intermediate.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.intermediate.dense.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.layernorm_after.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.layernorm_after.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.layernorm_before.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.layernorm_before.weight": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.output.dense.bias": "model-00002-of-00003.safetensors", "encoder.vision_tower.encoder.layers.3.blocks.1.output.dense.weight": "model-00002-of-00003.safetensors", "lm_head.weight": "model-00003-of-00003.safetensors", "shared.weight": "model-00001-of-00003.safetensors" } }