fix: remove phantom keys for unused last 16 RVQ layers from index

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7d7ef1f70796b5b7bbf1277c8d61ae0ec4879ac9f5a92ca06af3fcfb21cfa5
-size 4932667368
+oid sha256:b0419c2b297a29d68a16ccd3f18f6317332263b056ba912adfa34eec6bc5fd22
+size 4983138608

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35f93f16e4a5cfa7b10a44fb233d48f6206dfd65f5f4ec16d4ef622e46e1051c
+oid sha256:d188c9d2e699636704569e4af7b66acf1feb6a35e9de78e73c8fe2edba8c1a09
 size 4915961640

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43305ea6285bb1eb55d3bb004c5dab05d9ebf3dd259b79f5e328f493f3f90a1f
-size 4983069760
+oid sha256:fc023862c4f8cbecf47fb30cdfe58a8f22298019680de5bffae926ac25ad137f
+size 4974673472

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8748f19c135e185febfc4964120b2246021f4bbb7104e11493248984f07fa79b
-size 1879339648
+oid sha256:9dcd2be961b4c4111af035bdb0b214e2093bac9f796e4be71ed8942a459a1d22
+size 1837264680

model.safetensors.index.json

@@ -1,41 +1,25 @@
 {
   "metadata": {
-    "total_parameters": 8489841664,
-    "total_size": 16979683328
+    "total_parameters": 8355492864,
+    "total_size": 16710985728
   },
   "weight_map": {
-    "emb_ext.0.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.1.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.10.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.11.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.12.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.13.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.14.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.15.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.16.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.17.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.18.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.19.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.2.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.20.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.21.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.22.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.23.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.24.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.25.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.26.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.27.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.28.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.29.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.3.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.30.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.31.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.4.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.5.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.6.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.7.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.8.weight": "model-00004-of-00004.safetensors",
-    "emb_ext.9.weight": "model-00004-of-00004.safetensors",
+    "emb_ext.0.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.1.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.10.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.11.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.12.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.13.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.14.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.15.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.2.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.3.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.4.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.5.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.6.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.7.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.8.weight": "model-00001-of-00004.safetensors",
+    "emb_ext.9.weight": "model-00001-of-00004.safetensors",
     "language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
@@ -202,17 +186,17 @@
     "language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
     "language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -354,19 +338,19 @@
     "language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
-    "language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
-    "language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
-    "language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
     "language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -422,17 +406,17 @@
     "language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
     "language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
     "language_model.norm.weight": "model-00004-of-00004.safetensors",
     "lm_heads.0.weight": "model-00004-of-00004.safetensors",
     "lm_heads.1.weight": "model-00004-of-00004.safetensors",
@@ -443,24 +427,8 @@
     "lm_heads.14.weight": "model-00004-of-00004.safetensors",
     "lm_heads.15.weight": "model-00004-of-00004.safetensors",
     "lm_heads.16.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.17.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.18.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.19.weight": "model-00004-of-00004.safetensors",
     "lm_heads.2.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.20.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.21.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.22.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.23.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.24.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.25.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.26.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.27.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.28.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.29.weight": "model-00004-of-00004.safetensors",
     "lm_heads.3.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.30.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.31.weight": "model-00004-of-00004.safetensors",
-    "lm_heads.32.weight": "model-00004-of-00004.safetensors",
     "lm_heads.4.weight": "model-00004-of-00004.safetensors",
     "lm_heads.5.weight": "model-00004-of-00004.safetensors",
     "lm_heads.6.weight": "model-00004-of-00004.safetensors",