Upload model

config.json

@@ -0,0 +1,15 @@
+{
+  "_name_or_path": "/mnt/sda/dongkeun/checkpoints_final/metamath-langbridge-20b",
+  "alignments": "linear",
+  "architectures": [
+    "LangBridgeModel"
+  ],
+  "dim_enc": 4096,
+  "dim_lm": 5120,
+  "enc": "DKYoon/mt5-xxl-lm-adapt",
+  "freeze_encoder": true,
+  "freeze_language_model": true,
+  "lm": "meta-math/MetaMath-13B-V1.0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.2"
+}

generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.35.2"
+}

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8715cfbe981dca8e9e619777da5e2eb6de20640667c6d180206c3e816890b9c7
+size 4968289352

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e922b4fb655f51a3232fb62f13b641c233fb2a695dbc9505fcc3807a1ead6bf6
+size 4932729792

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a29d3db0500e1f5b1fe1680485157ef1efd750fd31c19d6af0afedb95bb2fae
+size 4951060040

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed2e2a34ebd469fd894edf2f61732868d4f553ea0754aae486ab2e98207ca420
+size 4933701456

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb394daee25b1490261b4583302f10e6502fc5c88b5a1cd0cfc878fdd2b392b0
+size 4933722216

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9062220089d54568a04d689a32c44e548527dea95918959dcd13ecb26b467e5
+size 4933722208

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec098f11a4e0ba0f1ea23f4c2c0531fa97789442a192faabc190b51b7b420a68
+size 4970422256

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddff0a2002abc56adb8edc6b900a0a4df9822922714e0d8be67ed8bf0bc1367d
+size 2760482880

model.safetensors.index.json

@@ -0,0 +1,592 @@
+{
+  "metadata": {
+    "total_size": 37384058880
+  },
+  "weight_map": {
+    "lb.alignment.enc_eos": "model-00003-of-00008.safetensors",
+    "lb.alignment.linear.bias": "model-00003-of-00008.safetensors",
+    "lb.alignment.linear.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00008.safetensors",
+    "lb.enc.encoder.final_layer_norm.weight": "model-00003-of-00008.safetensors",
+    "lb.enc.shared.weight": "model-00001-of-00008.safetensors",
+    "lb.lm.embed_tokens.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.0.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.1.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.10.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.10.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.11.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.12.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.12.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.12.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.12.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.16.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.17.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.18.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.19.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.2.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.20.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.20.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.20.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.20.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.20.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.20.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.20.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.20.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.20.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
+    "lb.lm.layers.21.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.21.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.22.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.23.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.24.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.25.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.26.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.input_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.27.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
+    "lb.lm.layers.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.29.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.3.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.3.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.30.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.32.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.33.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.34.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.input_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.35.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.36.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.36.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.36.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
+    "lb.lm.layers.36.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.37.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.38.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.input_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.39.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
+    "lb.lm.layers.4.input_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.4.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
+    "lb.lm.layers.5.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.5.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.6.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.7.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.8.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.input_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.layers.9.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
+    "lb.lm.norm.weight": "model-00008-of-00008.safetensors",
+    "lb.lm_head.weight": "model-00008-of-00008.safetensors"
+  }
+}