Update Speech Tower Training

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9c2767e164f2b9b55e4d0ce820060ee8d6c598e93d1e1198af79ece435bbeb
-size 4947827632
+oid sha256:50ce2ca9a606e392f358238a46dde5a6c80e49c6a3003684d01414dcb2d308de
+size 4976361384

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:637e4e661506aea30a973ed41cf2a2e90f265978299593a9d85a212b4b741fb0
-size 4987779168
+oid sha256:76d33ea4b80b03815fe7b548012f178745f8fe002809095649a38c3b575ac387
+size 4984907872

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c39b3ae5dd2b255a74e20c75a0fbb5ca8e3b3a930baf158a6555e157d70766a3
-size 1949903376
+oid sha256:0545c917ea3319c9c591e3680c4f222e6a19bfb1d5f246e21370f0c13d6d1e7c
+size 732141104

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 11885195552
+    "total_size": 10693095712
   },
   "weight_map": {
     "audio_projector.0.bias": "model-00001-of-00003.safetensors",
@@ -1400,19 +1400,19 @@
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
@@ -1427,87 +1427,87 @@
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
@@ -1539,29 +1539,29 @@
     "language_model.model.base_model.model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
@@ -1724,19 +1724,19 @@
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
@@ -1755,29 +1755,29 @@
     "language_model.model.base_model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",

speech/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f18cc6d64bb6708ff7e7e41c7b1b20813d085425832c2f82ce46e5652f65075
-size 2384262280
+oid sha256:79ae32ecb217238bdcb2b82d2fec12d5e980b163ada3c1f47f0d30ff97c39a12
+size 1192162472