Training in progress, step 200

config.json

@@ -12,6 +12,6 @@
   "speaker_emb_dim": 192,
   "step_duration": 0.08,
   "step_size": 1920,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.0"
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1"
 }

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717bb3ccd9f50a66c3db76f4a203989c8cf84e9bddb05e619aec63837b75b0bf
+size 4977169744

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6ed1f397f5698c7ba191c00b1870e6877e618982295f9c0220853bbae98641e
+size 4999813560

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d16c449b19d927dd998d0dfeb04ac6637ed6de1244f66f63ad9e775bc5ed902
+size 4999813600

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a2b0687143e1190234132190fb18e50b1395d8443ebb5c66df488c80a15c0f
+size 4832007920

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e7942cb0ca718b02d9a00241edb25e52a77ead052896ea6483c86885ba00a9
+size 4999813600

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:205616a8c02608a7de6d0144be793e3bd0f4dd63b26d1d677a60fbd6a67c6e2e
+size 4977219176

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c1edad572c4f97146fd1da752da97c5f682a5d3b7a486548bf05a76d9dcf8f3
+size 2236068288

model.safetensors.index.json

@@ -1,450 +1,450 @@
 {
   "metadata": {
-    "total_size": 16010925980
+    "total_size": 32021851960
   },
   "weight_map": {
-    "adapter.bias": "model-00004-of-00004.safetensors",
-    "adapter.weight": "model-00004-of-00004.safetensors",
-    "asr_head.weight": "model-00004-of-00004.safetensors",
-    "codec_decoding_heads.0.weight": "model-00003-of-00004.safetensors",
-    "codec_decoding_heads.1.weight": "model-00003-of-00004.safetensors",
-    "codec_decoding_heads.2.weight": "model-00003-of-00004.safetensors",
-    "codec_decoding_heads.3.weight": "model-00003-of-00004.safetensors",
-    "codec_decoding_heads.4.weight": "model-00003-of-00004.safetensors",
-    "codec_decoding_heads.5.weight": "model-00004-of-00004.safetensors",
-    "codec_decoding_heads.6.weight": "model-00004-of-00004.safetensors",
-    "codec_decoding_heads.7.weight": "model-00004-of-00004.safetensors",
-    "layer_norm.bias": "model-00004-of-00004.safetensors",
-    "layer_norm.weight": "model-00004-of-00004.safetensors",
-    "learned_layer_weight": "model-00001-of-00004.safetensors",
-    "listener.downsample.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.0.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.0.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.1.block.1.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.1.block.1.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.1.block.3.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.1.block.3.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.10.block.1.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.10.block.1.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.10.block.3.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.10.block.3.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.12.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.12.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.14.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.14.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.3.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.3.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.4.block.1.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.4.block.1.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.4.block.3.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.4.block.3.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.6.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.6.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.7.block.1.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.7.block.1.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.7.block.3.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.7.block.3.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.9.conv.bias": "model-00004-of-00004.safetensors",
-    "listener.embeddings.layers.9.conv.weight": "model-00004-of-00004.safetensors",
-    "listener.layer_weights": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.0.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.1.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.2.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.3.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.4.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.5.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.6.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.input_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.mlp.fc1.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.mlp.fc2.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.mlp_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.post_attention_layernorm.bias": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
-    "listener.model.layers.7.self_attn_layer_scale.scale": "model-00004-of-00004.safetensors",
-    "lm_head.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "lm_model.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "lm_model.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "lm_model.model.norm.weight": "model-00003-of-00004.safetensors",
-    "loss_fct.weight": "model-00004-of-00004.safetensors",
-    "speaker_adapter.bias": "model-00004-of-00004.safetensors",
-    "speaker_adapter.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.0.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.1.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.2.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.3.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.4.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.5.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.6.weight": "model-00004-of-00004.safetensors",
-    "tts_decoding_heads.7.weight": "model-00004-of-00004.safetensors",
-    "tts_head.weight": "model-00004-of-00004.safetensors"
+    "adapter.bias": "model-00007-of-00007.safetensors",
+    "adapter.weight": "model-00007-of-00007.safetensors",
+    "asr_head.weight": "model-00007-of-00007.safetensors",
+    "codec_decoding_heads.0.weight": "model-00006-of-00007.safetensors",
+    "codec_decoding_heads.1.weight": "model-00006-of-00007.safetensors",
+    "codec_decoding_heads.2.weight": "model-00006-of-00007.safetensors",
+    "codec_decoding_heads.3.weight": "model-00006-of-00007.safetensors",
+    "codec_decoding_heads.4.weight": "model-00006-of-00007.safetensors",
+    "codec_decoding_heads.5.weight": "model-00007-of-00007.safetensors",
+    "codec_decoding_heads.6.weight": "model-00007-of-00007.safetensors",
+    "codec_decoding_heads.7.weight": "model-00007-of-00007.safetensors",
+    "layer_norm.bias": "model-00007-of-00007.safetensors",
+    "layer_norm.weight": "model-00007-of-00007.safetensors",
+    "learned_layer_weight": "model-00001-of-00007.safetensors",
+    "listener.downsample.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.0.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.0.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.1.block.1.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.1.block.1.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.1.block.3.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.1.block.3.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.10.block.1.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.10.block.1.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.10.block.3.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.10.block.3.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.12.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.12.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.14.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.14.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.3.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.3.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.4.block.1.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.4.block.1.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.4.block.3.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.4.block.3.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.6.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.6.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.7.block.1.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.7.block.1.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.7.block.3.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.7.block.3.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.9.conv.bias": "model-00007-of-00007.safetensors",
+    "listener.embeddings.layers.9.conv.weight": "model-00007-of-00007.safetensors",
+    "listener.layer_weights": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.0.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.1.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.2.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.3.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.4.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.5.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.6.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.input_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.mlp.fc1.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.mlp.fc2.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.mlp_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "listener.model.layers.7.self_attn_layer_scale.scale": "model-00007-of-00007.safetensors",
+    "lm_head.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "lm_model.model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "lm_model.model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.27.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "lm_model.model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.30.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.31.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "lm_model.model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "lm_model.model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "lm_model.model.norm.weight": "model-00006-of-00007.safetensors",
+    "loss_fct.weight": "model-00007-of-00007.safetensors",
+    "speaker_adapter.bias": "model-00007-of-00007.safetensors",
+    "speaker_adapter.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.0.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.1.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.2.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.3.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.4.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.5.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.6.weight": "model-00007-of-00007.safetensors",
+    "tts_decoding_heads.7.weight": "model-00007-of-00007.safetensors",
+    "tts_head.weight": "model-00007-of-00007.safetensors"
   }
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a10cdf5ecd4cc99e59e285543ee619593d93d04e536071168ffce0aefa41e5e3
-size 7672
+oid sha256:1b4881cbe8f71ec4be1c9f79f6f5f81ad63d4e833bd53a3acd0d38679866d6ba
+size 7864