Upload folder using huggingface_hub

config.json

@@ -40,11 +40,22 @@
           "re:.*k_proj",
           "re:.*v_proj"
         ],
-        "weights": null
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": null,
+          "num_bits": 8,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "tensor",
+          "symmetric": true,
+          "type": "float"
+        }
       }
     },
     "format": "naive-quantized",
-    "global_compression_ratio": 1.0,
+    "global_compression_ratio": 1.1739105431057084,
     "ignore": [
       "model.layers.0.self_attn.o_proj",
       "model.layers.0.mlp.gate_proj",

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332f3faca76512c2bf3b0588fc1c0fad46e18d92e95b155f6de5565e13863533
-size 4976812448
+oid sha256:577cb6c36484fe3446089be233ecc0c4168a1fcc7910fb50e712d0fb5e867fb0
+size 4926497628

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839f7f4646a8abf3f834b7e38e89bee67d38cf3ce3ca13b943d34ce7ebd33845
-size 4999954440
+oid sha256:c38eacae5ba49a2c1a9abf81b7ec10e319d7a85f0e6b3197af8741449b2d550f
+size 4932866792

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf2e7a95112cb574a4af7665b04bed064ce49738a9bb7edf42b0420df6d4696
-size 4916055272
+oid sha256:6f2e80996d5166f73108cae825c941c5f81e4b01c4c3a1e84973afed055d07e6
+size 4345628484

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e9ad31c8c32abf3a55ee7fc7217b3ecb35fd3c74d98a5bd233e0e4d6964f46
-size 1168138808
+oid sha256:674610adfedb7f19d21475a7280d6b34774894e654f1d50f4c24444ba7bd0d04
+size 1050673280

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 16060915712
+    "total_size": 15255609536
   },
   "weight_map": {
     "lm_head.weight": "model-00004-of-00004.safetensors",
@@ -12,11 +12,14 @@
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -24,11 +27,14 @@
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -36,11 +42,14 @@
     "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -48,11 +57,14 @@
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -60,11 +72,14 @@
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -72,11 +87,14 @@
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -84,11 +102,14 @@
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -96,11 +117,14 @@
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -108,11 +132,14 @@
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -120,11 +147,14 @@
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -132,11 +162,14 @@
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
@@ -144,11 +177,14 @@
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -156,35 +192,44 @@
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -192,11 +237,14 @@
     "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -204,11 +252,14 @@
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -216,11 +267,14 @@
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -228,11 +282,14 @@
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -240,11 +297,14 @@
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -252,11 +312,14 @@
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -264,11 +327,14 @@
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -276,11 +342,14 @@
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -288,11 +357,14 @@
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
@@ -300,23 +372,29 @@
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.output_scale": "model-00003-of-00004.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -324,11 +402,14 @@
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -336,11 +417,14 @@
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -348,11 +432,14 @@
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -360,11 +447,14 @@
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
@@ -372,23 +462,29 @@
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.output_scale": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.output_scale": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.output_scale": "model-00002-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.norm.weight": "model-00004-of-00004.safetensors"
+    "model.layers.9.self_attn.k_proj.output_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.output_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.output_scale": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
   }
 }

recipe.yaml

@@ -2,7 +2,8 @@ quant_stage:
   quant_modifiers:
     QuantizationModifier:
       config_groups:
-        fp8_attention_q_proj:
+        fp8_attention_qkv_proj:
+          weights: {num_bits: 8, type: float, strategy: tensor}
           output_activations: {num_bits: 8, type: float, strategy: channel, dynamic: false,
             symmetric: true}
           targets: ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']