fix(gptq) remove un-used bias

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f567240506b6432a7c91f62dbf3abdd045f3c4b1013bbd4808ff596ad1846708
-size 3983817824
+oid sha256:195211506e67a8dfe1a0556ee3c23a54279b5537fc8492f527f61dc586888ee9
+size 3982678800

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e41d9af09037c50f37b14d9f20b04f984ebde3259545641aa8206b8c21361b20
-size 2945657232
+oid sha256:4a29e3934dd9229fdd28c6b1b678f5b3b7826020183ea87a7a06ad13ff7efd20
+size 2944261096

model.safetensors.index.json

@@ -1,22 +1,19 @@
 {
   "metadata": {
-    "total_size": 6929318912
+    "total_size": 6926795776
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -27,7 +24,6 @@
     "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -43,17 +39,14 @@
     "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -64,7 +57,6 @@
     "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -80,17 +72,14 @@
     "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -101,7 +90,6 @@
     "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -117,17 +105,14 @@
     "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -138,7 +123,6 @@
     "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -154,17 +138,14 @@
     "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -175,7 +156,6 @@
     "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -191,17 +171,14 @@
     "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -212,7 +189,6 @@
     "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -228,17 +204,14 @@
     "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -249,7 +222,6 @@
     "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -265,17 +237,14 @@
     "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -286,7 +255,6 @@
     "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -302,17 +270,14 @@
     "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -323,7 +288,6 @@
     "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -339,17 +303,14 @@
     "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -360,7 +321,6 @@
     "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -376,17 +336,14 @@
     "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -397,7 +354,6 @@
     "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -413,17 +369,14 @@
     "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -434,7 +387,6 @@
     "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -450,17 +402,14 @@
     "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -471,7 +420,6 @@
     "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -487,17 +435,14 @@
     "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -508,7 +453,6 @@
     "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -524,17 +468,14 @@
     "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -545,7 +486,6 @@
     "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -561,17 +501,14 @@
     "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -582,7 +519,6 @@
     "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -598,17 +534,14 @@
     "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -619,7 +552,6 @@
     "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -635,17 +567,14 @@
     "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -656,7 +585,6 @@
     "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -672,17 +600,14 @@
     "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -693,7 +618,6 @@
     "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -709,17 +633,14 @@
     "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -730,7 +651,6 @@
     "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -746,17 +666,14 @@
     "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -767,7 +684,6 @@
     "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -783,17 +699,14 @@
     "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -804,7 +717,6 @@
     "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -820,17 +732,14 @@
     "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -841,7 +750,6 @@
     "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -857,17 +765,14 @@
     "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -878,7 +783,6 @@
     "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -894,17 +798,14 @@
     "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -915,7 +816,6 @@
     "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -931,17 +831,14 @@
     "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -952,7 +849,6 @@
     "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -968,17 +864,14 @@
     "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -989,7 +882,6 @@
     "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -1005,17 +897,14 @@
     "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -1026,7 +915,6 @@
     "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",