diff --git "a/model.safetensors.index.json" "b/model.safetensors.index.json"
--- "a/model.safetensors.index.json"
+++ "b/model.safetensors.index.json"
@@ -1,21 +1,18 @@
 {
   "metadata": {
-    "total_size": 8659937280
+    "total_size": 8655677440
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.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",
@@ -23,38 +20,31 @@
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -62,38 +52,31 @@
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -101,38 +84,31 @@
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -140,38 +116,31 @@
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -179,38 +148,31 @@
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -218,38 +180,31 @@
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -257,38 +212,31 @@
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -296,38 +244,31 @@
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -335,38 +276,31 @@
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -374,38 +308,31 @@
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -413,38 +340,31 @@
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -452,38 +372,31 @@
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.scales": "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",
@@ -491,38 +404,31 @@
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -530,38 +436,31 @@
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -569,38 +468,31 @@
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -608,38 +500,31 @@
     "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
@@ -647,38 +532,31 @@
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.scales": "model-00001-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",
@@ -686,38 +564,31 @@
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "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",
     "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "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.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",
@@ -725,38 +596,31 @@
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "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",
     "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "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.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",
@@ -764,38 +628,31 @@
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "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",
     "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "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.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",
@@ -803,38 +660,31 @@
     "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "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",
     "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "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.28.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -842,38 +692,31 @@
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -881,38 +724,31 @@
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.scales": "model-00002-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",
@@ -920,38 +756,31 @@
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.30.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -959,38 +788,31 @@
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -998,38 +820,31 @@
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.32.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1037,38 +852,31 @@
     "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.33.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1076,38 +884,31 @@
     "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.34.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1115,38 +916,31 @@
     "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.35.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1154,38 +948,31 @@
     "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.36.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.36.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.36.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1193,38 +980,31 @@
     "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.36.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.36.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.36.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1232,38 +1012,31 @@
     "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.37.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.37.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.38.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.38.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.38.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1271,38 +1044,31 @@
     "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.38.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.38.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.38.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.38.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.38.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.38.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.39.mlp.down_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.down_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.39.mlp.gate_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.gate_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.39.mlp.up_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.up_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
@@ -1310,38 +1076,31 @@
     "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.39.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.k_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.39.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.o_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.39.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.q_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
-    "model.layers.39.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.v_proj.g_idx": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
     "model.layers.39.self_attn.v_proj.scales": "model-00002-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",
@@ -1349,38 +1108,31 @@
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -1388,38 +1140,31 @@
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -1427,38 +1172,31 @@
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -1466,38 +1204,31 @@
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -1505,38 +1236,31 @@
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "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.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",
@@ -1544,23 +1268,19 @@
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.g_idx": "model-00001-of-00002.safetensors",
     "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",
     "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.g_idx": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",