Upload GemmaForSequenceClassification

config.json

@@ -1,7 +1,7 @@
 {
   "_name_or_path": "RM_.._Lr5e-6_Epoch1",
   "architectures": [
-    "GemmaModel"
+    "GemmaForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b340949a558fd0c48e7fd7907b287a264ed6d816d1a0060c5f9e929f9b58d1e
-size 4911634832
+oid sha256:72142e596851acaa5c3d1dca420c793270fa4e69ba4a83c6bdb8721e170ce458
+size 4911635192

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1284e0b3dde16152f83dc25e143b9c37d9190aaeef4272fe9f92ab1c8e826a07
-size 4978829984
+oid sha256:e6b40aa7d8d6ae17d87c16c18b654ca48ffe7704ac76d135dfc7e6eeddfea7bb
+size 4978830584

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8dbdc76a24d64cb8dbb894ee4fb749bd31ae00598319c6a1400fe4c42735f8
-size 134242736
+oid sha256:0297e3e178eb0639c0fd368d2c428a2113e90a0661ea034d779c260505a780dc
+size 134251032

model.safetensors.index.json

@@ -1,171 +1,172 @@
 {
   "metadata": {
-    "total_size": 10024689664
+    "total_size": 10024697856
   },
   "weight_map": {
-    "embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
-    "layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
-    "layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "norm.weight": "model-00003-of-00003.safetensors"
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
   }
 }