Upload entire model folder

config.json

@@ -0,0 +1,14 @@
+{
+  "alignments": "linear",
+  "architectures": [
+    "LangBridgeModel"
+  ],
+  "dim_enc": 1024,
+  "dim_lm": 4096,
+  "enc": "castorini/afriteva_v2_large",
+  "freeze_encoder": true,
+  "freeze_language_model": true,
+  "lm": "llama-lang-adapt/MetaMath-Mistral-LayerSpecific",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.2"
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.37.2"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67aa854dbfe5e85c298da5dda51d11c87f8cd2b43756a1542556baaa695d7557
+size 4885941222

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf005532acc78e9074aa7cc1a8979c3f9d4cd0439086cf2e06eb7e51f523ed3c
+size 4915938762

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f4ad1a9f57e336cacebecb2262815926e27595e783f7c1220d71f023030a746
+size 4999843272

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88fddac228e00fc2ee36916cd4db05d466265b00cc254f6dacda03040a87a38c
+size 614501547

pytorch_model.bin.index.json

@@ -0,0 +1,522 @@
+{
+  "metadata": {
+    "total_size": 15416044544
+  },
+  "weight_map": {
+    "lb.alignment.enc_eos": "pytorch_model-00001-of-00004.bin",
+    "lb.alignment.linear.bias": "pytorch_model-00001-of-00004.bin",
+    "lb.alignment.linear.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.embeddings.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.enc.shared.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "lb.lm.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "lb.lm.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "lb.lm.norm.weight": "pytorch_model-00004-of-00004.bin",
+    "lb.lm_head.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}