Upload ParlerTTSForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/home/akhil/parler-tts/output_dir_training_mix_only/checkpoint-200000-epoch-143",
+  "_name_or_path": "/home/akhil/parler-tts/output_dir_training_mix_only_large/checkpoint-40000-epoch-28",
   "architectures": [
     "ParlerTTSForConditionalGeneration"
   ],
@@ -75,7 +75,7 @@
     "use_bfloat16": false
   },
   "decoder": {
-    "_name_or_path": "/fsx/yoach/tmp/artefacts/parler-tts-large-v2/decoder",
+    "_name_or_path": "./parler-tts-untrained-4B/decoder",
     "activation_dropout": 0.0,
     "activation_function": "gelu",
     "add_cross_attention": true,
@@ -101,7 +101,7 @@
     "finetuning_task": null,
     "forced_bos_token_id": null,
     "forced_eos_token_id": null,
-    "hidden_size": 1536,
+    "hidden_size": 2048,
     "id2label": {
       "0": "LABEL_0",
       "1": "LABEL_1"
@@ -120,13 +120,13 @@
     "min_length": 0,
     "model_type": "parler_tts_decoder",
     "no_repeat_ngram_size": 0,
-    "num_attention_heads": 24,
+    "num_attention_heads": 32,
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_codebooks": 9,
-    "num_cross_attention_key_value_heads": 24,
-    "num_hidden_layers": 32,
-    "num_key_value_heads": 8,
+    "num_cross_attention_key_value_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 32,
     "num_return_sequences": 1,
     "output_attentions": false,
     "output_hidden_states": false,
@@ -163,9 +163,9 @@
   "is_encoder_decoder": true,
   "model_type": "parler_tts",
   "pad_token_id": 1024,
-  "prompt_cross_attention": true,
+  "prompt_cross_attention": false,
   "text_encoder": {
-    "_name_or_path": "google/flan-t5-xl",
+    "_name_or_path": "google/flan-t5-large",
     "add_cross_attention": false,
     "architectures": [
       "T5ForConditionalGeneration"
@@ -176,9 +176,9 @@
     "chunk_size_feed_forward": 0,
     "classifier_dropout": 0.0,
     "cross_attention_hidden_size": null,
-    "d_ff": 5120,
+    "d_ff": 2816,
     "d_kv": 64,
-    "d_model": 2048,
+    "d_model": 1024,
     "decoder_start_token_id": 0,
     "dense_act_fn": "gelu_new",
     "diversity_penalty": 0.0,
@@ -214,7 +214,7 @@
     "num_beam_groups": 1,
     "num_beams": 1,
     "num_decoder_layers": 24,
-    "num_heads": 32,
+    "num_heads": 16,
     "num_layers": 24,
     "num_return_sequences": 1,
     "output_attentions": false,
@@ -233,35 +233,7 @@
     "return_dict_in_generate": false,
     "sep_token_id": null,
     "suppress_tokens": null,
-    "task_specific_params": {
-      "summarization": {
-        "early_stopping": true,
-        "length_penalty": 2.0,
-        "max_length": 200,
-        "min_length": 30,
-        "no_repeat_ngram_size": 3,
-        "num_beams": 4,
-        "prefix": "summarize: "
-      },
-      "translation_en_to_de": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to German: "
-      },
-      "translation_en_to_fr": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to French: "
-      },
-      "translation_en_to_ro": {
-        "early_stopping": true,
-        "max_length": 300,
-        "num_beams": 4,
-        "prefix": "translate English to Romanian: "
-      }
-    },
+    "task_specific_params": null,
     "temperature": 1.0,
     "tf_legacy_loss": false,
     "tie_encoder_decoder": false,
@@ -269,7 +241,7 @@
     "tokenizer_class": null,
     "top_k": 50,
     "top_p": 1.0,
-    "torch_dtype": "float32",
+    "torch_dtype": null,
     "torchscript": false,
     "typical_p": 1.0,
     "use_bfloat16": false,

generation_config.json

@@ -5,8 +5,4 @@
   "eos_token_id": 1024,
   "pad_token_id": 1024,
   "transformers_version": "4.40.2"
-  "max_length": 2580,
-  "min_new_tokens": 500,
-  "do_sample": true,
-  "guidance_scale": 1,
-}
+}

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c30d2151a8a9c3343b6998eeec019b46db9d17b84ef234d98ea6723941c2851c
-size 4984365952
+oid sha256:d928a2cef77c2bdd645f4e2c961b7a2ccfe0359fc93fd80f7e3bc9cd8523c34c
+size 4973817832

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:447e63a6259cea547ee9fc022c44da7355f186f60d6cb6c66a6386bae5fb23f8
-size 4805000272
+oid sha256:8a6c922b30c2fd9a322e5030818a30fff0b092d9687e9e16c8f59db3ce0c1ff8
+size 4983909552

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94e39b62ef3e7a14a0de2621ed68c9c244bfc9b255d5b9e17b7f8d570e380b03
-size 222560488
+oid sha256:48544df339c7da39c37abc0044e641b1ae7552598e5e7580c310cddc8d03c0b8
+size 637103896

model.safetensors.index.json

@@ -1,127 +1,127 @@
 {
   "metadata": {
-    "total_size": 10011788744
+    "total_size": 10594684360
   },
   "weight_map": {
     "audio_encoder.model.decoder.model.0.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.model.decoder.model.0.weight_g": "model-00001-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.0.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.0.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.1.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.2.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.3.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_v": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.5.alpha": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.6.bias": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.6.weight_g": "model-00002-of-00003.safetensors",
-    "audio_encoder.model.decoder.model.6.weight_v": "model-00002-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.0.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.2.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.3.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.1.block.4.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.2.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.3.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.2.block.4.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.2.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.3.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.3.block.4.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.2.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.3.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.0.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.1.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.1.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.2.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.3.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.4.block.4.block.3.weight_v": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.5.alpha": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.6.bias": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.6.weight_g": "model-00001-of-00003.safetensors",
+    "audio_encoder.model.decoder.model.6.weight_v": "model-00001-of-00003.safetensors",
     "audio_encoder.model.encoder.block.0.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.model.encoder.block.0.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.model.encoder.block.0.weight_v": "model-00001-of-00003.safetensors",
@@ -304,123 +304,123 @@
     "audio_encoder.model.quantizer.quantizers.8.out_proj.bias": "model-00001-of-00003.safetensors",
     "audio_encoder.model.quantizer.quantizers.8.out_proj.weight_g": "model-00001-of-00003.safetensors",
     "audio_encoder.model.quantizer.quantizers.8.out_proj.weight_v": "model-00001-of-00003.safetensors",
-    "decoder.lm_heads.0.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.1.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.2.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.3.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.4.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.5.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.6.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.7.weight": "model-00002-of-00003.safetensors",
-    "decoder.lm_heads.8.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_positions.weights": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.0.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.3.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.4.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.5.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.6.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.7.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.embed_tokens.8.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.lm_heads.0.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.1.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.2.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.3.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.4.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.5.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.6.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.7.weight": "model-00003-of-00003.safetensors",
+    "decoder.lm_heads.8.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.embed_positions.weights": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.0.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.3.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.4.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.5.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.6.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.7.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.embed_tokens.8.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layer_norm.bias": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.13.fc1.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.13.fc2.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.13.final_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.13.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.14.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.14.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.14.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
@@ -517,22 +517,22 @@
     "decoder.model.decoder.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.19.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.20.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.20.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.20.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
@@ -693,22 +693,22 @@
     "decoder.model.decoder.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.29.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.29.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "decoder.model.decoder.layers.30.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.30.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.30.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
@@ -741,106 +741,169 @@
     "decoder.model.decoder.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.31.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
     "decoder.model.decoder.layers.31.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.fc1.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.fc2.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
-    "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
-    "embed_positions.weights": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.fc1.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.fc2.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.32.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.fc1.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.fc2.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.final_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.33.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.encoder_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.fc1.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.fc2.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn.out_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn_layer_norm.bias": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.34.self_attn_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.encoder_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.fc1.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.fc2.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.final_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn.out_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn_layer_norm.bias": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.35.self_attn_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.encoder_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.fc1.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.fc2.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.final_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.final_layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00003.safetensors",
+    "decoder.model.decoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00003.safetensors",
     "embed_prompts.weight": "model-00003-of-00003.safetensors",
-    "enc_to_dec_proj.bias": "model-00002-of-00003.safetensors",
-    "enc_to_dec_proj.weight": "model-00002-of-00003.safetensors",
+    "enc_to_dec_proj.bias": "model-00003-of-00003.safetensors",
+    "enc_to_dec_proj.weight": "model-00003-of-00003.safetensors",
     "text_encoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
     "text_encoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
     "text_encoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",