Upload quantized model Qwen3.5-9B-AutoRound-MXFP8

README.md

@@ -25,9 +25,9 @@ This is a **MXFP8** quantization of [Qwen/Qwen3.5-9B](https://huggingface.co/Qwe
 
 | Benchmark | Score |
 |---|---|
-| gsm8k | 0.9393 |
-| hellaswag | 0.7796 |
-| mmlu | 0.7848 |
-| piqa | 0.7971 |
+| gsm8k | 0.9416 |
+| hellaswag | 0.7792 |
+| mmlu | 0.7827 |
+| piqa | 0.7949 |
 
 _Produced with [autoquant-agent](https://github.com/) — agent-driven quantize + evaluate + self-heal._

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fee3a86de3472780518cbf03dc44abdd72b801177ecc6e7f2a07fa43748e6579
-size 2163921200
+oid sha256:ed81c8641bf094ef26cec03489febc558bf534133a61aadbdac17dac4356366b
+size 2163921232

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 0
+    "total_size": 12374342624
   },
   "weight_map": {
     "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
@@ -264,6 +264,8 @@
     "model.language_model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -273,6 +275,8 @@
     "model.language_model.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -282,6 +286,8 @@
     "model.language_model.layers.10.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -301,6 +307,8 @@
     "model.language_model.layers.12.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.in_proj_qkv.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
@@ -312,6 +320,8 @@
     "model.language_model.layers.13.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.in_proj_qkv.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
@@ -323,6 +333,8 @@
     "model.language_model.layers.14.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -342,6 +354,8 @@
     "model.language_model.layers.16.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -351,6 +365,8 @@
     "model.language_model.layers.17.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -360,6 +376,8 @@
     "model.language_model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -379,6 +397,8 @@
     "model.language_model.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -388,6 +408,8 @@
     "model.language_model.layers.20.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -397,6 +419,8 @@
     "model.language_model.layers.21.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.in_proj_qkv.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
@@ -408,6 +432,8 @@
     "model.language_model.layers.22.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -427,6 +453,8 @@
     "model.language_model.layers.24.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -436,6 +464,8 @@
     "model.language_model.layers.25.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -445,6 +475,8 @@
     "model.language_model.layers.26.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -464,6 +496,8 @@
     "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.in_proj_qkv.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
@@ -475,6 +509,8 @@
     "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.in_proj_qkv.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
@@ -496,6 +532,8 @@
     "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -515,6 +553,8 @@
     "model.language_model.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -524,6 +564,8 @@
     "model.language_model.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -533,6 +575,8 @@
     "model.language_model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -552,6 +596,8 @@
     "model.language_model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -561,6 +607,8 @@
     "model.language_model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.A_log": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.dt_bias": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.in_proj_z.weight_scale": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.norm.weight": "model-00004-of-00004.safetensors",
@@ -581,77 +629,29 @@
     "mtp.norm.weight": "model-00004-of-00004.safetensors",
     "mtp.pre_fc_norm_hidden.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00004-of-00004.safetensors",
-    "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00004-of-00004.safetensors",
     "model.visual.blocks.0.attn.proj.bias": "model-00004-of-00004.safetensors",
     "model.visual.blocks.0.attn.proj.weight": "model-00004-of-00004.safetensors",
     "model.visual.blocks.0.attn.qkv.bias": "model-00004-of-00004.safetensors",