Upload Gemma3OmniForConditionalGeneration

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7ff9a4ed297ee12e666fb9f7fe6f8b8d0e8c5ed919ea4e786774e78c77a378
-size 4972360200
+oid sha256:6857bd0f3da7ac4908d0c13377d244edddf5b9c26bb835366fb75abfa44ca03d
+size 4961210712

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481a875b34ca20f649a66bd1317a321994fe31ab495964bb125b21b49652b7ad
-size 1911307432
+oid sha256:1595b9f723870954083d1e1121dc56b26d95c060961c98ee007c761f7aae121e
+size 707897312

model.safetensors.index.json

@@ -1,7 +1,7 @@
 {
   "metadata": {
-    "total_parameters": 3441758976,
-    "total_size": 6883517952
+    "total_parameters": 2834501632,
+    "total_size": 5669003264
   },
   "weight_map": {
     "language_model.model.embed_tokens.weight": "model-00001-of-00002.safetensors",
@@ -70,97 +70,97 @@
     "language_model.model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
@@ -174,32 +174,32 @@
     "language_model.model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "language_model.model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.post_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.pre_feedforward_layernorm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "language_model.model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "language_model.model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "language_model.model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
@@ -380,18 +380,6 @@
     "model.audio_projector.projector.backbone.layers.2.self_attn.in_proj_weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.projector.backbone.layers.2.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.projector.backbone.layers.2.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.linear1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.linear1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.linear2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.linear2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.norm1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.norm1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.norm2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.norm2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.self_attn.in_proj_bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.self_attn.in_proj_weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.projector.backbone.layers.3.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.projector.norm.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.projector.norm.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.projector.out.weight": "model-00001-of-00002.safetensors",
@@ -462,126 +450,6 @@
     "model.audio_projector.whisper_encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.2.fc1.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.2.fc1.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.2.fc2.bias": "model-00001-of-00002.safetensors",
@@ -597,156 +465,6 @@
     "model.audio_projector.whisper_encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.3.fc1.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.3.fc1.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.3.fc2.bias": "model-00001-of-00002.safetensors",
@@ -762,36 +480,6 @@
     "model.audio_projector.whisper_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.fc1.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.fc1.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.fc2.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.fc2.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.final_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.final_layer_norm.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00002.safetensors",
-    "model.audio_projector.whisper_encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.4.fc1.bias": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.4.fc1.weight": "model-00001-of-00002.safetensors",
     "model.audio_projector.whisper_encoder.layers.4.fc2.bias": "model-00001-of-00002.safetensors",