update Quark quantized Auto Mixed Precision (AMP) Qwen3-8B model with better accuracies

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

generation_config.json

@@ -9,5 +9,5 @@
   "temperature": 0.6,
   "top_k": 20,
   "top_p": 0.95,
-  "transformers_version": "4.53.2"
+  "transformers_version": "4.55.1"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f83c1606ffbe89db0b967fe2b220a5e88aa345a7236044b1f8ac51d3b27b80
-size 4994147516
+oid sha256:80195867d013ceb7e1674b46866a8f64ca773aa27faf014dbb74de0d286465a2
+size 4998493600

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944c9956f0e3882db5fb87405310500916f10232101d893cb8d967a4ed8497d6
-size 1936860844
+oid sha256:32d964e03bf34ea5940d78d6840c95bbeaf9ea96069e2c8f97bf152afedd9268
+size 2789734872

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 5518963712,
-    "total_size": 6930917760
+    "total_parameters": 6433321984,
+    "total_size": 7788128960
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -10,8 +10,10 @@
     "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -32,6 +34,7 @@
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -46,6 +49,7 @@
     "model.layers.1.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -57,7 +61,6 @@
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -72,6 +75,7 @@
     "model.layers.10.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -83,10 +87,13 @@
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -95,6 +102,7 @@
     "model.layers.11.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -106,10 +114,13 @@
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -129,10 +140,13 @@
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -141,6 +155,7 @@
     "model.layers.13.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -154,8 +169,10 @@
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -164,6 +181,7 @@
     "model.layers.14.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -183,18 +201,22 @@
     "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -203,14 +225,17 @@
     "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -223,14 +248,17 @@
     "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -263,18 +291,22 @@
     "model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -285,14 +317,18 @@
     "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -325,14 +361,17 @@
     "model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -345,158 +384,163 @@
     "model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.post_attention_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.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.weight_scale": "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.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_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.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_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.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_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.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_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.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_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.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "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.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -507,14 +551,18 @@
     "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -527,22 +575,27 @@
     "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.post_attention_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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight_scale": "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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -567,14 +620,17 @@
     "model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.post_attention_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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.weight_scale": "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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
@@ -587,34 +643,42 @@
     "model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.post_attention_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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.weight_scale": "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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.post_attention_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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.weight_scale": "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.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.output_scale": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
@@ -622,8 +686,10 @@
     "model.layers.35.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
@@ -651,14 +717,18 @@
     "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -674,14 +744,18 @@
     "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight_scale": "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.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
@@ -701,6 +775,7 @@
     "model.layers.6.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -712,6 +787,7 @@
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -726,6 +802,7 @@
     "model.layers.7.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
@@ -740,8 +817,10 @@
     "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
@@ -776,6 +855,7 @@
     "model.layers.9.self_attn.k_proj.output_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -231,7 +231,7 @@
   "eos_token": "<|endoftext|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 2048,
+  "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
   "padding_side": "left",
   "split_special_tokens": false,