Upload model.safetensors.index.json

model.safetensors.index.json

@@ -1,12 +1,12 @@
 {
   "metadata": {
-    "total_size": 6173383680
+    "total_size": 6173219840
   },
   "weight_map": {
     "model.decoder.embed_positions.weight": "model-00001-of-00002.safetensors",
     "model.decoder.embed_tokens.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.decoder.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "model.decoder.layer_norm.bias": "model-00002-of-00002.safetensors",
+    "model.decoder.layer_norm.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.encoder_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -22,7 +22,6 @@
     "model.decoder.layers.0.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.0.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -47,7 +46,6 @@
     "model.decoder.layers.1.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.1.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -72,7 +70,6 @@
     "model.decoder.layers.10.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.10.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -97,7 +94,6 @@
     "model.decoder.layers.11.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.11.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -122,7 +118,6 @@
     "model.decoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.12.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -147,7 +142,6 @@
     "model.decoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.13.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -172,7 +166,6 @@
     "model.decoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.14.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -197,7 +190,6 @@
     "model.decoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.15.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -222,7 +214,6 @@
     "model.decoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.16.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -247,7 +238,6 @@
     "model.decoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.17.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -272,7 +262,6 @@
     "model.decoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.18.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -297,7 +286,6 @@
     "model.decoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.19.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -322,7 +310,6 @@
     "model.decoder.layers.2.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.2.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -347,7 +334,6 @@
     "model.decoder.layers.20.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.20.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.20.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.20.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -372,7 +358,6 @@
     "model.decoder.layers.21.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.21.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.21.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.21.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -397,7 +382,6 @@
     "model.decoder.layers.22.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.22.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.22.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.22.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.22.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -422,7 +406,6 @@
     "model.decoder.layers.23.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.23.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.23.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.23.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -447,7 +430,6 @@
     "model.decoder.layers.24.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.24.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.24.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.24.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.24.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.24.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -472,7 +454,6 @@
     "model.decoder.layers.25.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.25.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.25.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.25.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.25.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.25.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -497,7 +478,6 @@
     "model.decoder.layers.26.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.26.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.26.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.26.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.26.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.26.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -522,7 +502,6 @@
     "model.decoder.layers.27.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.27.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.27.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.27.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.27.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.27.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -547,7 +526,6 @@
     "model.decoder.layers.28.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.28.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.28.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.28.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.28.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.28.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -572,7 +550,6 @@
     "model.decoder.layers.29.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.29.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.29.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.29.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.29.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.29.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -597,7 +574,6 @@
     "model.decoder.layers.3.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.3.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -622,7 +598,6 @@
     "model.decoder.layers.30.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.30.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.30.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.30.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.30.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.30.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -647,7 +622,6 @@
     "model.decoder.layers.31.fc2.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.31.final_layer_norm.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.31.final_layer_norm.weight": "model-00002-of-00002.safetensors",
-    "model.decoder.layers.31.no_speech_bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.decoder.layers.31.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
     "model.decoder.layers.31.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
@@ -672,7 +646,6 @@
     "model.decoder.layers.4.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.4.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -697,7 +670,6 @@
     "model.decoder.layers.5.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.5.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -722,7 +694,6 @@
     "model.decoder.layers.6.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.6.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -747,7 +718,6 @@
     "model.decoder.layers.7.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.7.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -772,7 +742,6 @@
     "model.decoder.layers.8.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.8.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
@@ -797,7 +766,6 @@
     "model.decoder.layers.9.fc2.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.decoder.layers.9.no_speech_bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",