update

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/opt/llama3.1/Meta-Llama-3.1-8B-Instruct/",
+  "_name_or_path": "/opt/zhiyu/ckpts/Meta-Llama-3.1-8B-Instruct/",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -33,7 +33,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.43.4",
+  "transformers_version": "4.44.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   ],
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.43.4"
+  "transformers_version": "4.44.0"
 }

hf_quant_config.json

@@ -1,10 +1,13 @@
 {
     "producer": {
         "name": "modelopt",
-        "version": "0.17.0"
+        "version": "0.23.0"
     },
     "quantization": {
         "quant_algo": "FP8",
-        "kv_cache_quant_algo": null
+        "kv_cache_quant_algo": "FP8",
+        "exclude_modules": [
+            "lm_head"
+        ]
     }
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d160581591a70c3a0fcc48e3b706e5f4134fc7f1b727ed9604c793c44386105f
-size 4997853640
+oid sha256:0d44feba7a89792817523bcd648e695cfd457c2ce41b67dcdea4a01b9a59d1f3
+size 4997857356

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cde34f06818ff1a59b6080042a85aa642a8b90097cf3b5d5a15c43a4b9df686
-size 4083427008
+oid sha256:4ade51d4b47f5bab5e04c110514351ca8a1fa176055fb1bdab4e4844bf18e8b8
+size 4083429684

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 9081202432
+    "total_size": 9081202688
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -17,6 +17,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.k_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.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -26,6 +27,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.v_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",
@@ -40,6 +42,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -49,6 +52,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.v_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",
@@ -63,6 +67,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -72,6 +77,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.v_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",
@@ -86,6 +92,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -95,6 +102,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.v_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",
@@ -109,6 +117,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.k_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.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -118,6 +127,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.v_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",
@@ -132,6 +142,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -141,6 +152,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.v_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",
@@ -155,6 +167,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -164,6 +177,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.v_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",
@@ -178,6 +192,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -187,6 +202,7 @@
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.v_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",
@@ -201,6 +217,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -210,6 +227,7 @@
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.v_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",
@@ -224,6 +242,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -233,6 +252,7 @@
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.v_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",
@@ -247,6 +267,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -256,6 +277,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.v_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",
@@ -270,6 +292,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -279,6 +302,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.v_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",
@@ -293,6 +317,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -302,6 +327,7 @@
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.v_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",
@@ -316,6 +342,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -325,6 +352,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.v_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",
@@ -339,6 +367,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -348,6 +377,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.v_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",
@@ -362,6 +392,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -371,6 +402,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.v_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",
@@ -385,6 +417,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -394,6 +427,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.v_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",
@@ -408,6 +442,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -417,6 +452,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.v_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",
@@ -431,6 +467,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -440,6 +477,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.v_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",
@@ -454,6 +492,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -463,6 +502,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.v_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",
@@ -477,6 +517,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -486,6 +527,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.v_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",
@@ -500,6 +542,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.28.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -509,6 +552,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.v_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",
@@ -523,6 +567,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -532,6 +577,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.v_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",
@@ -546,6 +592,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -555,6 +602,7 @@
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.v_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",
@@ -569,6 +617,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.k_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -578,6 +627,7 @@
     "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.v_proj.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.v_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",
@@ -592,6 +642,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.k_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.o_proj.input_scale": "model-00002-of-00002.safetensors",
@@ -601,6 +652,7 @@
     "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.input_scale": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.v_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",
@@ -615,6 +667,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -624,6 +677,7 @@
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.v_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",
@@ -638,6 +692,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -647,6 +702,7 @@
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.v_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",
@@ -661,6 +717,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -670,6 +727,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.v_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",
@@ -684,6 +742,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -693,6 +752,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.v_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",
@@ -707,6 +767,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.k_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.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -716,6 +777,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.v_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",
@@ -730,6 +792,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.k_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00002.safetensors",
@@ -739,6 +802,7 @@
     "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.input_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.v_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"

tokenizer_config.json

@@ -2058,5 +2058,6 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }