Upload folder using huggingface_hub

config.json

@@ -12,6 +12,7 @@
   "hidden_size": 4096,
   "initializer_range": 0.02,
   "intermediate_size": 11008,
+  "kv_cache_torch_dtype": "float8_e4m3fn",
   "max_position_embeddings": 4096,
   "mlp_bias": false,
   "model_type": "llama",
@@ -23,7 +24,7 @@
   "rope_scaling": null,
   "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float8_e4m3fn",
+  "torch_dtype": "float16",
   "training_pipeline_parallel": 1,
   "training_tensor_parallel": 1,
   "transformers_version": "4.41.0.dev0",

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f444f466b42e06ad78e9c690b730fec321c55a404791f81f0c918a644cf35e58
-size 4938987913
+oid sha256:1bc13df452e3bf7d2de5dedba696e0d885135bb77ee02fcef06d5e8a569cfb8d
+size 4938986320

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89e17b1f9c5a181922f8802f380452e5609ac99ea526a3d07f9bebb3b0f31ac
-size 4947393368
+oid sha256:9b03992ed6dc4a5e2bdf9205004c822719a1d35610c7e0b59cf6f9cbfe94dfd1
+size 4947391856

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3ef429c06eb0360ba1e166f0dafa9d9a5b959896bbdb1d4881d1bad4517c33
-size 3590490472
+oid sha256:a2ee9355229dd5f2ef06a1e41ed29ddbb9ac8d4504ed87be946bfef2560716fb
+size 3590489464

model.safetensors.index.json

@@ -1,17 +1,15 @@
 {
   "metadata": {
-    "total_size": 13476831425
+    "total_size": 13476831360
   },
   "weight_map": {
     "lm_head.weight": "model-00003-of-00003.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
-    "model.kv_cache_dtype": "model-00001-of-00003.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.0.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -22,7 +20,6 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.1.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -33,7 +30,6 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.10.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -44,7 +40,6 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.11.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -55,7 +50,6 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.12.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -66,7 +60,6 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.13.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -77,7 +70,6 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.14.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -88,7 +80,6 @@
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.15.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -99,7 +90,6 @@
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.16.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -110,7 +100,6 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.17.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -121,7 +110,6 @@
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.18.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -132,7 +120,6 @@
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.19.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -143,7 +130,6 @@
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.2.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -154,7 +140,6 @@
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.20.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -165,7 +150,6 @@
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.21.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -176,7 +160,6 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "model.layers.22.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -187,7 +170,6 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.23.self_attn.k_proj.output_quantizer._amax": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.kv_scale": "model-00002-of-00003.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
@@ -198,7 +180,6 @@
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.24.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -209,7 +190,6 @@
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.25.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -220,7 +200,6 @@
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.26.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -231,7 +210,6 @@
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.27.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -242,7 +220,6 @@
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.28.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -253,7 +230,6 @@
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.29.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -264,7 +240,6 @@
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.3.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -275,7 +250,6 @@
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.30.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -286,7 +260,6 @@
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "model.layers.31.self_attn.k_proj.output_quantizer._amax": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.kv_scale": "model-00003-of-00003.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
@@ -297,7 +270,6 @@
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.4.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -308,7 +280,6 @@
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.5.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -319,7 +290,6 @@
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.6.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -330,7 +300,6 @@
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.7.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -341,7 +310,6 @@
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.8.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
@@ -352,7 +320,6 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
-    "model.layers.9.self_attn.k_proj.output_quantizer._amax": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.kv_scale": "model-00001-of-00003.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",