Fix weight mismatch

config.json

@@ -26,7 +26,7 @@
   "qk_norm": "l2",
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.48.2",
   "use_beta": true,
   "use_cache": true,
   "use_gate": false,

generation_config.json

@@ -2,5 +2,6 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.45.2"
+  "pad_token_id": 2,
+  "transformers_version": "4.48.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c27696ee022ac2f5bbf84fcdba6485563bc63838eb82905128aa1d060dd7548
+oid sha256:c079868b8f9c695c5dd2f4837ac4b0d2cdf67cf50540cdbcd926d8c2a3ae2e63
 size 4979631520

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65674a0d4dcd22152506a0208842565a53b272024090d252358f178f1377c3f5
+oid sha256:390c1da40aecbe6fa6829a7c51612f103d27ed1b840aba612f7c54e0dd038ba3
 size 428786768

model.safetensors.index.json

@@ -8,419 +8,419 @@
     "model.layers.0.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.31.attn.b_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.k_conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.attn.norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.o_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.q_conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.v_conv1d.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.attn.norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.o_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.q_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.v_conv1d.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.attn_norm.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.norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }
 }