Upload LlamaForCausalLM

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c2ca4c30b93362e674c9e9b8db1f61c4e1a76420811a13a4af65027bf4678d
-size 4985669136
+oid sha256:88aa6434480d8cdd983dc47ae2520b527f51486dc6c9c33acd1ff7c1e38420a5
+size 4979633592

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ab9608fb2b142285267bbce9d1b73c482b2921a28c3126d7e3315bcbdb7cbc
-size 4964437296
+oid sha256:d2a0aee196878f8a241d4aa98dd82abe72934c87423a73dc204cb608b23218f9
+size 4957876888

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13326cf9166a23c426f6f839d1a2338fb81a5aff4575727727f4adc5325a07f6
-size 4006532344
+oid sha256:3e038ddce280fccdad76371f29f847b2670948302b4a61f723c737a14a6df771
+size 4002333672

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 13956587520
+    "total_size": 13939810304
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
@@ -12,12 +12,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.v_proj.lora_B.default.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",
@@ -25,12 +21,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.v_proj.lora_B.default.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-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -38,12 +30,8 @@
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-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",
@@ -51,12 +39,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-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",
@@ -64,12 +48,8 @@
     "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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.v_proj.lora_B.default.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",
@@ -77,12 +57,8 @@
     "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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.v_proj.lora_B.default.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",
@@ -90,12 +66,8 @@
     "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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.v_proj.lora_B.default.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",
@@ -103,12 +75,8 @@
     "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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.v_proj.lora_B.default.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",
@@ -116,12 +84,8 @@
     "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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.v_proj.lora_B.default.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-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -129,12 +93,8 @@
     "model.layers.17.post_attention_layernorm.weight": "model-00002-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.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.v_proj.lora_B.default.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.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -142,12 +102,8 @@
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -155,12 +111,8 @@
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.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",
@@ -168,12 +120,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.v_proj.lora_B.default.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.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -181,12 +129,8 @@
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -194,12 +138,8 @@
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
@@ -207,12 +147,8 @@
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -220,12 +156,8 @@
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00003.safetensors",
-    "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -233,12 +165,8 @@
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -246,12 +174,8 @@
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -259,12 +183,8 @@
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -272,12 +192,8 @@
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -285,12 +201,8 @@
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -298,12 +210,8 @@
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-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",
@@ -311,12 +219,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.v_proj.lora_B.default.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.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -324,12 +228,8 @@
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
@@ -337,12 +237,8 @@
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-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",
@@ -350,12 +246,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.v_proj.lora_B.default.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",
@@ -363,12 +255,8 @@
     "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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.v_proj.lora_B.default.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-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -376,12 +264,8 @@
     "model.layers.6.post_attention_layernorm.weight": "model-00001-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.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.v_proj.lora_B.default.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-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -389,12 +273,8 @@
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -402,12 +282,8 @@
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
@@ -415,12 +291,8 @@
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"
   }
 }