Upload MoshiForConditionalGeneration

config.json

@@ -136,7 +136,7 @@
   "sliding_window": 3000,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.45.0.dev0",
+  "transformers_version": "4.46.0.dev0",
   "use_cache": true,
   "vocab_size": 32000
 }

generation_config.json

@@ -8,11 +8,11 @@
     "min_length": 9,
     "temperature": 0.8,
     "top_k": 250,
-    "transformers_version": "4.45.0.dev0"
+    "transformers_version": "4.46.0.dev0"
   },
   "do_sample": true,
   "pad_token_id": 2048,
   "temp": 0.7,
   "top_k": 25,
-  "transformers_version": "4.45.0.dev0"
+  "transformers_version": "4.46.0.dev0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1d825685ccdf9b095c2dbeb41412b7ca3e26709e231adb855f8cadf63670e1e
-size 4967882346
+oid sha256:6750271c959be958cce253176e398d2df5539ba6e92c54dda4255fcb702155cc
+size 4967882658

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f14b1258fd15ddfdbbb1ad5fb8c887b7f45dbb7bd48f09f22657da5db1dd22a
-size 4932709968
+oid sha256:3a3826c15c32bd1d1e098d473b5c4db24448aeefdce24faa0f386bde110f406c
+size 4932710304

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1fada36de5f3bdb3e46d98cc213511b0b83aee451dc7ec3bf342932992bbcd
-size 4970984376
+oid sha256:3e81ddb665ad64c1aadabfe94aa908557138b9526f1fb041ded5947c82d61611
+size 4970984712

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361e8e630ac8e756944626a177a27d2055c1074c163a456e39e031794b8c2218
-size 696274256
+oid sha256:30f5734936c31b510b803f31058c592c647d1d407a6bc64b0fdf00c70122e46e
+size 696274344

model.safetensors.index.json

@@ -359,258 +359,258 @@
     "decoder.model.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.0.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.0.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.0.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.0.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.1.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.1.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.1.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.1.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.10.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.10.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.10.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.10.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.10.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.10.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.11.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.11.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.11.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.11.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.11.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.11.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.12.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.12.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.12.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.12.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.12.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.12.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.13.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.13.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.13.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.13.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.13.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.13.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.14.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.14.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.14.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.14.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.14.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.14.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.15.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.15.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.15.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.15.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.15.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.15.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.16.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.16.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.16.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.16.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.16.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.16.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.17.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.17.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.17.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.17.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.17.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.17.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.18.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.18.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.18.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.18.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.18.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.18.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.19.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.19.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.19.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.19.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.19.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.19.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.2.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.2.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.2.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.2.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.20.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.20.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.20.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.20.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.20.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.20.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.21.mlp.fc1.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.21.mlp.fc2.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.21.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.21.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.21.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.21.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.22.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.22.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "decoder.model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.22.self_attn.k_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.22.self_attn.o_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.22.self_attn.q_proj.linear.weight": "model-00002-of-00004.safetensors",
+    "decoder.model.layers.22.self_attn.v_proj.linear.weight": "model-00002-of-00004.safetensors",
     "decoder.model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.23.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.23.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.23.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.23.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.23.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.23.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.24.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.24.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.24.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.24.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.24.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.24.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.25.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.25.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.25.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.25.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.25.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.25.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.26.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.26.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.26.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.26.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.26.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.26.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.27.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.27.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.27.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.27.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.27.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.27.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.28.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.28.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.28.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.28.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.28.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.28.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.29.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.29.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.29.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.29.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.29.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.29.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.3.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.3.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.3.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.3.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.30.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.30.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.30.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.30.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.30.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.30.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.31.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.31.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "decoder.model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.31.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.31.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.31.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "decoder.model.layers.31.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "decoder.model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.4.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.4.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.4.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.4.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.5.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.5.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.5.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.5.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.6.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.6.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.6.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.6.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.7.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.7.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.7.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.7.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.8.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.8.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.8.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.8.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
     "decoder.model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "decoder.model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.9.self_attn.k_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.9.self_attn.o_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.9.self_attn.q_proj.linear.weight": "model-00001-of-00004.safetensors",
+    "decoder.model.layers.9.self_attn.v_proj.linear.weight": "model-00001-of-00004.safetensors",
     "decoder.model.norm.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.embed_tokens.0.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.embed_tokens.1.weight": "model-00003-of-00004.safetensors",
@@ -624,50 +624,50 @@
     "depth_decoder.layers.0.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.0.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.0.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.0.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.0.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.0.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.0.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.1.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.1.mlp.fc2.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.1.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.1.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.1.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.1.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.1.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.1.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.1.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.2.mlp.fc1.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.2.mlp.fc2.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.2.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.2.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "depth_decoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.2.self_attn.k_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.2.self_attn.o_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.2.self_attn.q_proj.linear.weight": "model-00003-of-00004.safetensors",
+    "depth_decoder.layers.2.self_attn.v_proj.linear.weight": "model-00003-of-00004.safetensors",
     "depth_decoder.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.3.mlp.fc1.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.3.mlp.fc2.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.3.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.3.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.3.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.3.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.4.mlp.fc1.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.4.mlp.fc2.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.4.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.4.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.4.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.4.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.5.mlp.fc1.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.5.mlp.fc2.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
-    "depth_decoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.5.self_attn.k_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.5.self_attn.o_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.5.self_attn.q_proj.linear.weight": "model-00004-of-00004.safetensors",
+    "depth_decoder.layers.5.self_attn.v_proj.linear.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.lm_heads.weight": "model-00004-of-00004.safetensors",
     "depth_decoder.text_embed_tokens.weight": "model-00003-of-00004.safetensors",
     "embed_tokens.0.weight": "model-00001-of-00004.safetensors",