Add files using upload-large-folder tool

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "alpindale/magnum-v2-12b-fp8",
+  "_name_or_path": "./magnum-v2-12b",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -22,12 +22,12 @@
         "input_activations": {
           "actorder": null,
           "block_structure": null,
-          "dynamic": true,
+          "dynamic": false,
           "group_size": null,
           "num_bits": 8,
-          "observer": null,
+          "observer": "minmax",
           "observer_kwargs": {},
-          "strategy": "token",
+          "strategy": "tensor",
           "symmetric": true,
           "type": "float"
         },
@@ -43,18 +43,29 @@
           "num_bits": 8,
           "observer": "minmax",
           "observer_kwargs": {},
-          "strategy": "channel",
+          "strategy": "tensor",
           "symmetric": true,
           "type": "float"
         }
       }
     },
     "format": "float-quantized",
-    "global_compression_ratio": 1.4619965155281183,
+    "global_compression_ratio": 1.5303030117505458,
     "ignore": [
       "lm_head"
     ],
-    "kv_cache_scheme": null,
+    "kv_cache_scheme": {
+      "actorder": null,
+      "block_structure": null,
+      "dynamic": false,
+      "group_size": null,
+      "num_bits": 8,
+      "observer": "minmax",
+      "observer_kwargs": {},
+      "strategy": "tensor",
+      "symmetric": true,
+      "type": "float"
+    },
     "quant_method": "compressed-tensors",
     "quantization_status": "compressed"
   },
@@ -63,7 +74,7 @@
   "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.0.dev0",
   "use_cache": false,
   "vocab_size": 131072
-}
+}

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "do_sample": true,
   "eos_token_id": 2,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.48.0.dev0"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8da8895bd0ec6f62a0ea6e7317073d0f67fcfa3f2a84214df8bb3d3a8cd609e
-size 4940278960
+oid sha256:3b49b1066e077d4c78697a4d0b6474b7c1ea6d243cc1ebc3c64ba7f6233d5d41
+size 4939098516

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b4d4f3a9b15480bf0e134becec5937dacc7c29549c5a11d1b3ae5e8c551da9
-size 4982788792
+oid sha256:c54d454bb0e1cf4b2119ee21c62046b6772ffa3bf1b8cca0f1fdd60bbe85de7c
+size 4981154556

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2befbdffa4783b53e9a520b2d5b20d41026757c31d761cea4f1cdc51d05d06cb
-size 3670986576
+oid sha256:2c0dc394e65baceb2b087525dbd224152dbafadc8bbb34c9726303edf10e7736
+size 3670234960

model.safetensors.index.json

@@ -1,650 +1,1010 @@
 {
   "metadata": {
-    "total_size": 13593978880
+    "total_size": 13590375680
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.input_scale": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_scale": "model-00002-of-00003.safetensors",
     "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.36.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.37.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.38.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.k_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.input_scale": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
+    "model.layers.39.self_attn.v_scale": "model-00003-of-00003.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.input_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_scale": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"
   }
 }

recipe.yaml

@@ -1,6 +1,11 @@
-DEFAULT_stage:
-  DEFAULT_modifiers:
+quant_stage:
+  quant_modifiers:
     QuantizationModifier:
       ignore: [lm_head]
-      targets: [Linear]
-      scheme: FP8_DYNAMIC
+      config_groups:
+        group_0:
+          weights: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}
+          input_activations: {num_bits: 8, type: float, strategy: tensor, dynamic: false,
+            symmetric: true}
+          targets: [Linear]
+      kv_cache_scheme: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}