Upload model

model.safetensors.index.json

@@ -9,65 +9,65 @@
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00003-of-00005.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
@@ -75,16 +75,16 @@
     "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00003-of-00005.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
@@ -136,9 +136,9 @@
     "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
@@ -154,18 +154,18 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00004-of-00005.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00004-of-00005.safetensors",