Add files using upload-large-folder tool

model-missing-base.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2034aab30f47d55d7ec21f597273124453f9cb152690b0d504e77ca28ce3266
+size 110118080

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
     "total_parameters": 7941100832,
-    "total_size": 15882203604
+    "total_size": 15992314836
   },
   "weight_map": {
     "model.audio_tower.layers.0.feed_forward1.ffw_layer_1.input_max": "model-00002-of-00004.safetensors",
@@ -1059,9 +1059,12 @@
     "model.language_model.layers.24.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.24.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.24.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1073,9 +1076,12 @@
     "model.language_model.layers.25.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1087,9 +1093,12 @@
     "model.language_model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1101,9 +1110,12 @@
     "model.language_model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1115,9 +1127,12 @@
     "model.language_model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1129,9 +1144,12 @@
     "model.language_model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.3.layer_scalar": "model-00002-of-00004.safetensors",
     "model.language_model.layers.3.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
@@ -1160,9 +1178,12 @@
     "model.language_model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.30.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1174,9 +1195,12 @@
     "model.language_model.layers.31.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1188,9 +1212,12 @@
     "model.language_model.layers.32.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1202,9 +1229,12 @@
     "model.language_model.layers.33.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1216,9 +1246,12 @@
     "model.language_model.layers.34.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1230,9 +1263,12 @@
     "model.language_model.layers.35.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1244,9 +1280,12 @@
     "model.language_model.layers.36.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.36.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.36.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.36.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.37.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1258,9 +1297,12 @@
     "model.language_model.layers.37.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.37.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.37.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.37.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.38.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1272,9 +1314,12 @@
     "model.language_model.layers.38.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.38.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.38.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.38.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.38.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.38.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.39.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1286,9 +1331,12 @@
     "model.language_model.layers.39.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.39.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.39.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.39.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.39.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.39.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.4.layer_scalar": "model-00002-of-00004.safetensors",
     "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
@@ -1317,9 +1365,12 @@
     "model.language_model.layers.40.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.40.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.40.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.40.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.40.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.40.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.40.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.40.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.40.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.41.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.layer_scalar": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
@@ -1331,9 +1382,12 @@
     "model.language_model.layers.41.post_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.post_per_layer_input_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.pre_feedforward_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.41.self_attn.k_norm.weight": "model-missing-base.safetensors",
+    "model.language_model.layers.41.self_attn.k_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.41.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
     "model.language_model.layers.41.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.41.self_attn.v_proj.weight": "model-missing-base.safetensors",
     "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "model.language_model.layers.5.layer_scalar": "model-00002-of-00004.safetensors",
     "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",