Upload folder using huggingface_hub

config.json

@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -19,6 +20,10 @@
   "pretraining_tp": 1,
   "quantization_config": {
     "activation_scheme": "static",
+    "ignored_layers": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": "static",
     "quant_method": "fp8"
   },
   "rms_norm_eps": 1e-05,
@@ -26,7 +31,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.2",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.2"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ece24a0facf0a8c89bf678873700809caaea20d1831e2b8229d4525ca692341e
-size 4997855404
+oid sha256:673aaa8946ea4a0bbcb2cfd4feb53de88315293ca325e7e10d53ae2f2078e0cb
+size 4997855436

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b4345a801910f5b84b649b7e7bd0b786e79f2854836d59bc01d2b8ef8c1049
-size 4083428188
+oid sha256:58109c17ab43fd8313d732a3253b77ed64773039149412b3a860385d73274e87
+size 4083428220

model.safetensors.index.json

@@ -6,773 +6,773 @@
     "lm_head.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.0.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.1.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.10.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.11.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.12.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.13.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.14.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.15.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.16.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.17.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.18.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.18.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.19.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.2.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.20.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.21.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.22.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.23.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.24.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.25.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.3.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.kv_scale": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.act_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.6.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.8.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.down_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.gate_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.mlp.up_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.k_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.kv_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.o_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.q_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.v_proj.act_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }
-}
+}