Upload GemmaForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/gemma-2b",
+  "_name_or_path": "google/gemma-2b-it",
   "architectures": [
     "GemmaForCausalLM"
   ],

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98caad07f1e1d17fede7734906d6881d4cb231e1d0cd2ebcf7fc8a6317eee4d6
-size 4945242264
+oid sha256:d837772a5352183b1f446ca093742dd4c6f30407359aa5adee5c4270d7e82719
+size 4946579048

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3342a2f7db857bc9873c699eef1416eb2b320603e5e042a6f7736689b26382cb
+oid sha256:20fe2ee66bf1361241a6c522091a5e0328fc6c1703f93734889fa381fcf8760c
 size 67121608

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5012344832
+    "total_size": 5013671936
   },
   "weight_map": {
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -9,163 +9,235 @@
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.base_layer.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }