Upload folder using huggingface_hub

README.md

@@ -0,0 +1,24 @@
+---
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-to-speech
+tags:
+- model_hub_mixin
+- pytorch_model_hub_mixin
+- text-to-speech
+- mlx
+---
+
+# mlx-community/csm-1b-8bit
+This model was converted to MLX format from [`sesame/csm-1b`](https://huggingface.co/sesame/csm-1b) using mlx-audio version **0.1.1**.
+Refer to the [original model card](https://huggingface.co/sesame/csm-1b) for more details on the model.
+## Use with mlx
+
+```bash
+pip install -U mlx-audio
+```
+
+```bash
+python -m mlx_audio.tts.generate --model mlx-community/csm-1b-8bit --text "Describe this image."
+```

config.json

@@ -0,0 +1,1076 @@
+{
+    "_attn_implementation_autoset": false,
+    "add_cross_attention": false,
+    "architectures": null,
+    "audio_num_codebooks": 32,
+    "audio_vocab_size": 2051,
+    "backbone_flavor": "llama-1B",
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_flavor": "llama-100M",
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "mask_decoder_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
+        "hidden_size": 256,
+        "hidden_act": "relu",
+        "mlp_dim": 2048,
+        "num_hidden_layers": 2,
+        "num_attention_heads": 8,
+        "attention_downsample_rate": 2,
+        "num_multimask_outputs": 3,
+        "iou_head_depth": 3,
+        "iou_head_hidden_dim": 256,
+        "layer_norm_eps": 1e-06,
+        "model_type": ""
+    },
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "sam",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "prompt_encoder_config": {
+        "return_dict": true,
+        "output_hidden_states": false,
+        "output_attentions": false,
+        "torchscript": false,
+        "torch_dtype": null,
+        "use_bfloat16": false,
+        "tf_legacy_loss": false,
+        "pruned_heads": {},
+        "tie_word_embeddings": true,
+        "chunk_size_feed_forward": 0,
+        "is_encoder_decoder": false,
+        "is_decoder": false,
+        "cross_attention_hidden_size": null,
+        "add_cross_attention": false,
+        "tie_encoder_decoder": false,
+        "max_length": 20,
+        "min_length": 0,
+        "do_sample": false,
+        "early_stopping": false,
+        "num_beams": 1,
+        "num_beam_groups": 1,
+        "diversity_penalty": 0.0,
+        "temperature": 1.0,
+        "top_k": 50,
+        "top_p": 1.0,
+        "typical_p": 1.0,
+        "repetition_penalty": 1.0,
+        "length_penalty": 1.0,
+        "no_repeat_ngram_size": 0,
+        "encoder_no_repeat_ngram_size": 0,
+        "bad_words_ids": null,
+        "num_return_sequences": 1,
+        "output_scores": false,
+        "return_dict_in_generate": false,
+        "forced_bos_token_id": null,
+        "forced_eos_token_id": null,
+        "remove_invalid_values": false,
+        "exponential_decay_length_penalty": null,
+        "suppress_tokens": null,
+        "begin_suppress_tokens": null,
+        "architectures": null,
+        "finetuning_task": null,
+        "id2label": {
+            "0": "LABEL_0",
+            "1": "LABEL_1"
+        },
+        "label2id": {
+            "LABEL_0": 0,
+            "LABEL_1": 1
+        },
+        "tokenizer_class": null,
+        "prefix": null,
+        "bos_token_id": null,
+        "pad_token_id": null,
+        "eos_token_id": null,
+        "sep_token_id": null,
+        "decoder_start_token_id": null,
+        "task_specific_params": null,
+        "problem_type": null,
+        "_name_or_path": "",
+        "_attn_implementation_autoset": false,
+        "hidden_size": 256,
+        "image_size": 1024,
+        "patch_size": 16,
+        "image_embedding_size": 64,
+        "mask_input_channels": 16,
+        "num_point_embeddings": 4,
+        "hidden_act": "gelu",
+        "layer_norm_eps": 1e-06,
+        "model_type": ""
+    },
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 8,
+        "model.backbone.embed_tokens": false,
+        "model.backbone.layers.0.self_attn.q_proj": true,
+        "model.backbone.layers.0.self_attn.k_proj": true,
+        "model.backbone.layers.0.self_attn.v_proj": true,
+        "model.backbone.layers.0.self_attn.o_proj": true,
+        "model.backbone.layers.0.self_attn.rope": false,
+        "model.backbone.layers.0.mlp.gate_proj": true,
+        "model.backbone.layers.0.mlp.down_proj": true,
+        "model.backbone.layers.0.mlp.up_proj": true,
+        "model.backbone.layers.0.input_layernorm": false,
+        "model.backbone.layers.0.post_attention_layernorm": false,
+        "model.backbone.layers.1.self_attn.q_proj": true,
+        "model.backbone.layers.1.self_attn.k_proj": true,
+        "model.backbone.layers.1.self_attn.v_proj": true,
+        "model.backbone.layers.1.self_attn.o_proj": true,
+        "model.backbone.layers.1.self_attn.rope": false,
+        "model.backbone.layers.1.mlp.gate_proj": true,
+        "model.backbone.layers.1.mlp.down_proj": true,
+        "model.backbone.layers.1.mlp.up_proj": true,
+        "model.backbone.layers.1.input_layernorm": false,
+        "model.backbone.layers.1.post_attention_layernorm": false,
+        "model.backbone.layers.2.self_attn.q_proj": true,
+        "model.backbone.layers.2.self_attn.k_proj": true,
+        "model.backbone.layers.2.self_attn.v_proj": true,
+        "model.backbone.layers.2.self_attn.o_proj": true,
+        "model.backbone.layers.2.self_attn.rope": false,
+        "model.backbone.layers.2.mlp.gate_proj": true,
+        "model.backbone.layers.2.mlp.down_proj": true,
+        "model.backbone.layers.2.mlp.up_proj": true,
+        "model.backbone.layers.2.input_layernorm": false,
+        "model.backbone.layers.2.post_attention_layernorm": false,
+        "model.backbone.layers.3.self_attn.q_proj": true,
+        "model.backbone.layers.3.self_attn.k_proj": true,
+        "model.backbone.layers.3.self_attn.v_proj": true,
+        "model.backbone.layers.3.self_attn.o_proj": true,
+        "model.backbone.layers.3.self_attn.rope": false,
+        "model.backbone.layers.3.mlp.gate_proj": true,
+        "model.backbone.layers.3.mlp.down_proj": true,
+        "model.backbone.layers.3.mlp.up_proj": true,
+        "model.backbone.layers.3.input_layernorm": false,
+        "model.backbone.layers.3.post_attention_layernorm": false,
+        "model.backbone.layers.4.self_attn.q_proj": true,
+        "model.backbone.layers.4.self_attn.k_proj": true,
+        "model.backbone.layers.4.self_attn.v_proj": true,
+        "model.backbone.layers.4.self_attn.o_proj": true,
+        "model.backbone.layers.4.self_attn.rope": false,
+        "model.backbone.layers.4.mlp.gate_proj": true,
+        "model.backbone.layers.4.mlp.down_proj": true,
+        "model.backbone.layers.4.mlp.up_proj": true,
+        "model.backbone.layers.4.input_layernorm": false,
+        "model.backbone.layers.4.post_attention_layernorm": false,
+        "model.backbone.layers.5.self_attn.q_proj": true,
+        "model.backbone.layers.5.self_attn.k_proj": true,
+        "model.backbone.layers.5.self_attn.v_proj": true,
+        "model.backbone.layers.5.self_attn.o_proj": true,
+        "model.backbone.layers.5.self_attn.rope": false,
+        "model.backbone.layers.5.mlp.gate_proj": true,
+        "model.backbone.layers.5.mlp.down_proj": true,
+        "model.backbone.layers.5.mlp.up_proj": true,
+        "model.backbone.layers.5.input_layernorm": false,
+        "model.backbone.layers.5.post_attention_layernorm": false,
+        "model.backbone.layers.6.self_attn.q_proj": true,
+        "model.backbone.layers.6.self_attn.k_proj": true,
+        "model.backbone.layers.6.self_attn.v_proj": true,
+        "model.backbone.layers.6.self_attn.o_proj": true,
+        "model.backbone.layers.6.self_attn.rope": false,
+        "model.backbone.layers.6.mlp.gate_proj": true,
+        "model.backbone.layers.6.mlp.down_proj": true,
+        "model.backbone.layers.6.mlp.up_proj": true,
+        "model.backbone.layers.6.input_layernorm": false,
+        "model.backbone.layers.6.post_attention_layernorm": false,
+        "model.backbone.layers.7.self_attn.q_proj": true,
+        "model.backbone.layers.7.self_attn.k_proj": true,
+        "model.backbone.layers.7.self_attn.v_proj": true,
+        "model.backbone.layers.7.self_attn.o_proj": true,
+        "model.backbone.layers.7.self_attn.rope": false,
+        "model.backbone.layers.7.mlp.gate_proj": true,
+        "model.backbone.layers.7.mlp.down_proj": true,
+        "model.backbone.layers.7.mlp.up_proj": true,
+        "model.backbone.layers.7.input_layernorm": false,
+        "model.backbone.layers.7.post_attention_layernorm": false,
+        "model.backbone.layers.8.self_attn.q_proj": true,
+        "model.backbone.layers.8.self_attn.k_proj": true,
+        "model.backbone.layers.8.self_attn.v_proj": true,
+        "model.backbone.layers.8.self_attn.o_proj": true,
+        "model.backbone.layers.8.self_attn.rope": false,
+        "model.backbone.layers.8.mlp.gate_proj": true,
+        "model.backbone.layers.8.mlp.down_proj": true,
+        "model.backbone.layers.8.mlp.up_proj": true,
+        "model.backbone.layers.8.input_layernorm": false,
+        "model.backbone.layers.8.post_attention_layernorm": false,
+        "model.backbone.layers.9.self_attn.q_proj": true,
+        "model.backbone.layers.9.self_attn.k_proj": true,
+        "model.backbone.layers.9.self_attn.v_proj": true,
+        "model.backbone.layers.9.self_attn.o_proj": true,
+        "model.backbone.layers.9.self_attn.rope": false,
+        "model.backbone.layers.9.mlp.gate_proj": true,
+        "model.backbone.layers.9.mlp.down_proj": true,
+        "model.backbone.layers.9.mlp.up_proj": true,
+        "model.backbone.layers.9.input_layernorm": false,
+        "model.backbone.layers.9.post_attention_layernorm": false,
+        "model.backbone.layers.10.self_attn.q_proj": true,
+        "model.backbone.layers.10.self_attn.k_proj": true,
+        "model.backbone.layers.10.self_attn.v_proj": true,
+        "model.backbone.layers.10.self_attn.o_proj": true,
+        "model.backbone.layers.10.self_attn.rope": false,
+        "model.backbone.layers.10.mlp.gate_proj": true,
+        "model.backbone.layers.10.mlp.down_proj": true,
+        "model.backbone.layers.10.mlp.up_proj": true,
+        "model.backbone.layers.10.input_layernorm": false,
+        "model.backbone.layers.10.post_attention_layernorm": false,
+        "model.backbone.layers.11.self_attn.q_proj": true,
+        "model.backbone.layers.11.self_attn.k_proj": true,
+        "model.backbone.layers.11.self_attn.v_proj": true,
+        "model.backbone.layers.11.self_attn.o_proj": true,
+        "model.backbone.layers.11.self_attn.rope": false,
+        "model.backbone.layers.11.mlp.gate_proj": true,
+        "model.backbone.layers.11.mlp.down_proj": true,
+        "model.backbone.layers.11.mlp.up_proj": true,
+        "model.backbone.layers.11.input_layernorm": false,
+        "model.backbone.layers.11.post_attention_layernorm": false,
+        "model.backbone.layers.12.self_attn.q_proj": true,
+        "model.backbone.layers.12.self_attn.k_proj": true,
+        "model.backbone.layers.12.self_attn.v_proj": true,
+        "model.backbone.layers.12.self_attn.o_proj": true,
+        "model.backbone.layers.12.self_attn.rope": false,
+        "model.backbone.layers.12.mlp.gate_proj": true,
+        "model.backbone.layers.12.mlp.down_proj": true,
+        "model.backbone.layers.12.mlp.up_proj": true,
+        "model.backbone.layers.12.input_layernorm": false,
+        "model.backbone.layers.12.post_attention_layernorm": false,
+        "model.backbone.layers.13.self_attn.q_proj": true,
+        "model.backbone.layers.13.self_attn.k_proj": true,
+        "model.backbone.layers.13.self_attn.v_proj": true,
+        "model.backbone.layers.13.self_attn.o_proj": true,
+        "model.backbone.layers.13.self_attn.rope": false,
+        "model.backbone.layers.13.mlp.gate_proj": true,
+        "model.backbone.layers.13.mlp.down_proj": true,
+        "model.backbone.layers.13.mlp.up_proj": true,
+        "model.backbone.layers.13.input_layernorm": false,
+        "model.backbone.layers.13.post_attention_layernorm": false,
+        "model.backbone.layers.14.self_attn.q_proj": true,
+        "model.backbone.layers.14.self_attn.k_proj": true,
+        "model.backbone.layers.14.self_attn.v_proj": true,
+        "model.backbone.layers.14.self_attn.o_proj": true,
+        "model.backbone.layers.14.self_attn.rope": false,
+        "model.backbone.layers.14.mlp.gate_proj": true,
+        "model.backbone.layers.14.mlp.down_proj": true,
+        "model.backbone.layers.14.mlp.up_proj": true,
+        "model.backbone.layers.14.input_layernorm": false,
+        "model.backbone.layers.14.post_attention_layernorm": false,
+        "model.backbone.layers.15.self_attn.q_proj": true,
+        "model.backbone.layers.15.self_attn.k_proj": true,
+        "model.backbone.layers.15.self_attn.v_proj": true,
+        "model.backbone.layers.15.self_attn.o_proj": true,
+        "model.backbone.layers.15.self_attn.rope": false,
+        "model.backbone.layers.15.mlp.gate_proj": true,
+        "model.backbone.layers.15.mlp.down_proj": true,
+        "model.backbone.layers.15.mlp.up_proj": true,
+        "model.backbone.layers.15.input_layernorm": false,
+        "model.backbone.layers.15.post_attention_layernorm": false,
+        "model.backbone.norm": false,
+        "model.decoder.embed_tokens": false,
+        "model.decoder.layers.0.self_attn.q_proj": true,
+        "model.decoder.layers.0.self_attn.k_proj": true,
+        "model.decoder.layers.0.self_attn.v_proj": true,
+        "model.decoder.layers.0.self_attn.o_proj": true,
+        "model.decoder.layers.0.self_attn.rope": false,
+        "model.decoder.layers.0.mlp.gate_proj": true,
+        "model.decoder.layers.0.mlp.down_proj": true,
+        "model.decoder.layers.0.mlp.up_proj": true,
+        "model.decoder.layers.0.input_layernorm": false,
+        "model.decoder.layers.0.post_attention_layernorm": false,
+        "model.decoder.layers.1.self_attn.q_proj": true,
+        "model.decoder.layers.1.self_attn.k_proj": true,
+        "model.decoder.layers.1.self_attn.v_proj": true,
+        "model.decoder.layers.1.self_attn.o_proj": true,
+        "model.decoder.layers.1.self_attn.rope": false,
+        "model.decoder.layers.1.mlp.gate_proj": true,
+        "model.decoder.layers.1.mlp.down_proj": true,
+        "model.decoder.layers.1.mlp.up_proj": true,
+        "model.decoder.layers.1.input_layernorm": false,
+        "model.decoder.layers.1.post_attention_layernorm": false,
+        "model.decoder.layers.2.self_attn.q_proj": true,
+        "model.decoder.layers.2.self_attn.k_proj": true,
+        "model.decoder.layers.2.self_attn.v_proj": true,
+        "model.decoder.layers.2.self_attn.o_proj": true,
+        "model.decoder.layers.2.self_attn.rope": false,
+        "model.decoder.layers.2.mlp.gate_proj": true,
+        "model.decoder.layers.2.mlp.down_proj": true,
+        "model.decoder.layers.2.mlp.up_proj": true,
+        "model.decoder.layers.2.input_layernorm": false,
+        "model.decoder.layers.2.post_attention_layernorm": false,
+        "model.decoder.layers.3.self_attn.q_proj": true,
+        "model.decoder.layers.3.self_attn.k_proj": true,
+        "model.decoder.layers.3.self_attn.v_proj": true,
+        "model.decoder.layers.3.self_attn.o_proj": true,
+        "model.decoder.layers.3.self_attn.rope": false,
+        "model.decoder.layers.3.mlp.gate_proj": true,
+        "model.decoder.layers.3.mlp.down_proj": true,
+        "model.decoder.layers.3.mlp.up_proj": true,
+        "model.decoder.layers.3.input_layernorm": false,
+        "model.decoder.layers.3.post_attention_layernorm": false,
+        "model.decoder.norm": false,
+        "model.text_embeddings": true,
+        "model.audio_embeddings": true,
+        "model.projection": true,
+        "model.codebook0_head": true,
+        "_audio_tokenizer.encoder.init_conv1d.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.0.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.1.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.2.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.3.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.final_conv1d.conv.conv": false,
+        "_audio_tokenizer.decoder.init_conv1d.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.1.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.2.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.3.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.final_conv1d.conv.conv": false,
+        "_audio_tokenizer.quantizer.rvq_first.input_proj": false,
+        "_audio_tokenizer.quantizer.rvq_first.output_proj": false,
+        "_audio_tokenizer.quantizer.rvq_first.vq.layers.0.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.input_proj": false,
+        "_audio_tokenizer.quantizer.rvq_rest.output_proj": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.0.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.1.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.2.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.3.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.4.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.5.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.6.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.7.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.8.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.9.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.10.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.11.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.12.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.13.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.14.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.15.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.16.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.17.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.18.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.19.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.20.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.21.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.22.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.23.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.24.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.25.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.26.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.27.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.28.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.29.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.30.codebook": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.rope": false,
+        "_audio_tokenizer.downsample.conv.conv.conv": false,
+        "_audio_tokenizer.upsample.convtr.convtr.convtr": false
+    },
+    "quantization_config": {
+        "group_size": 64,
+        "bits": 8,
+        "model.backbone.embed_tokens": false,
+        "model.backbone.layers.0.self_attn.q_proj": true,
+        "model.backbone.layers.0.self_attn.k_proj": true,
+        "model.backbone.layers.0.self_attn.v_proj": true,
+        "model.backbone.layers.0.self_attn.o_proj": true,
+        "model.backbone.layers.0.self_attn.rope": false,
+        "model.backbone.layers.0.mlp.gate_proj": true,
+        "model.backbone.layers.0.mlp.down_proj": true,
+        "model.backbone.layers.0.mlp.up_proj": true,
+        "model.backbone.layers.0.input_layernorm": false,
+        "model.backbone.layers.0.post_attention_layernorm": false,
+        "model.backbone.layers.1.self_attn.q_proj": true,
+        "model.backbone.layers.1.self_attn.k_proj": true,
+        "model.backbone.layers.1.self_attn.v_proj": true,
+        "model.backbone.layers.1.self_attn.o_proj": true,
+        "model.backbone.layers.1.self_attn.rope": false,
+        "model.backbone.layers.1.mlp.gate_proj": true,
+        "model.backbone.layers.1.mlp.down_proj": true,
+        "model.backbone.layers.1.mlp.up_proj": true,
+        "model.backbone.layers.1.input_layernorm": false,
+        "model.backbone.layers.1.post_attention_layernorm": false,
+        "model.backbone.layers.2.self_attn.q_proj": true,
+        "model.backbone.layers.2.self_attn.k_proj": true,
+        "model.backbone.layers.2.self_attn.v_proj": true,
+        "model.backbone.layers.2.self_attn.o_proj": true,
+        "model.backbone.layers.2.self_attn.rope": false,
+        "model.backbone.layers.2.mlp.gate_proj": true,
+        "model.backbone.layers.2.mlp.down_proj": true,
+        "model.backbone.layers.2.mlp.up_proj": true,
+        "model.backbone.layers.2.input_layernorm": false,
+        "model.backbone.layers.2.post_attention_layernorm": false,
+        "model.backbone.layers.3.self_attn.q_proj": true,
+        "model.backbone.layers.3.self_attn.k_proj": true,
+        "model.backbone.layers.3.self_attn.v_proj": true,
+        "model.backbone.layers.3.self_attn.o_proj": true,
+        "model.backbone.layers.3.self_attn.rope": false,
+        "model.backbone.layers.3.mlp.gate_proj": true,
+        "model.backbone.layers.3.mlp.down_proj": true,
+        "model.backbone.layers.3.mlp.up_proj": true,
+        "model.backbone.layers.3.input_layernorm": false,
+        "model.backbone.layers.3.post_attention_layernorm": false,
+        "model.backbone.layers.4.self_attn.q_proj": true,
+        "model.backbone.layers.4.self_attn.k_proj": true,
+        "model.backbone.layers.4.self_attn.v_proj": true,
+        "model.backbone.layers.4.self_attn.o_proj": true,
+        "model.backbone.layers.4.self_attn.rope": false,
+        "model.backbone.layers.4.mlp.gate_proj": true,
+        "model.backbone.layers.4.mlp.down_proj": true,
+        "model.backbone.layers.4.mlp.up_proj": true,
+        "model.backbone.layers.4.input_layernorm": false,
+        "model.backbone.layers.4.post_attention_layernorm": false,
+        "model.backbone.layers.5.self_attn.q_proj": true,
+        "model.backbone.layers.5.self_attn.k_proj": true,
+        "model.backbone.layers.5.self_attn.v_proj": true,
+        "model.backbone.layers.5.self_attn.o_proj": true,
+        "model.backbone.layers.5.self_attn.rope": false,
+        "model.backbone.layers.5.mlp.gate_proj": true,
+        "model.backbone.layers.5.mlp.down_proj": true,
+        "model.backbone.layers.5.mlp.up_proj": true,
+        "model.backbone.layers.5.input_layernorm": false,
+        "model.backbone.layers.5.post_attention_layernorm": false,
+        "model.backbone.layers.6.self_attn.q_proj": true,
+        "model.backbone.layers.6.self_attn.k_proj": true,
+        "model.backbone.layers.6.self_attn.v_proj": true,
+        "model.backbone.layers.6.self_attn.o_proj": true,
+        "model.backbone.layers.6.self_attn.rope": false,
+        "model.backbone.layers.6.mlp.gate_proj": true,
+        "model.backbone.layers.6.mlp.down_proj": true,
+        "model.backbone.layers.6.mlp.up_proj": true,
+        "model.backbone.layers.6.input_layernorm": false,
+        "model.backbone.layers.6.post_attention_layernorm": false,
+        "model.backbone.layers.7.self_attn.q_proj": true,
+        "model.backbone.layers.7.self_attn.k_proj": true,
+        "model.backbone.layers.7.self_attn.v_proj": true,
+        "model.backbone.layers.7.self_attn.o_proj": true,
+        "model.backbone.layers.7.self_attn.rope": false,
+        "model.backbone.layers.7.mlp.gate_proj": true,
+        "model.backbone.layers.7.mlp.down_proj": true,
+        "model.backbone.layers.7.mlp.up_proj": true,
+        "model.backbone.layers.7.input_layernorm": false,
+        "model.backbone.layers.7.post_attention_layernorm": false,
+        "model.backbone.layers.8.self_attn.q_proj": true,
+        "model.backbone.layers.8.self_attn.k_proj": true,
+        "model.backbone.layers.8.self_attn.v_proj": true,
+        "model.backbone.layers.8.self_attn.o_proj": true,
+        "model.backbone.layers.8.self_attn.rope": false,
+        "model.backbone.layers.8.mlp.gate_proj": true,
+        "model.backbone.layers.8.mlp.down_proj": true,
+        "model.backbone.layers.8.mlp.up_proj": true,
+        "model.backbone.layers.8.input_layernorm": false,
+        "model.backbone.layers.8.post_attention_layernorm": false,
+        "model.backbone.layers.9.self_attn.q_proj": true,
+        "model.backbone.layers.9.self_attn.k_proj": true,
+        "model.backbone.layers.9.self_attn.v_proj": true,
+        "model.backbone.layers.9.self_attn.o_proj": true,
+        "model.backbone.layers.9.self_attn.rope": false,
+        "model.backbone.layers.9.mlp.gate_proj": true,
+        "model.backbone.layers.9.mlp.down_proj": true,
+        "model.backbone.layers.9.mlp.up_proj": true,
+        "model.backbone.layers.9.input_layernorm": false,
+        "model.backbone.layers.9.post_attention_layernorm": false,
+        "model.backbone.layers.10.self_attn.q_proj": true,
+        "model.backbone.layers.10.self_attn.k_proj": true,
+        "model.backbone.layers.10.self_attn.v_proj": true,
+        "model.backbone.layers.10.self_attn.o_proj": true,
+        "model.backbone.layers.10.self_attn.rope": false,
+        "model.backbone.layers.10.mlp.gate_proj": true,
+        "model.backbone.layers.10.mlp.down_proj": true,
+        "model.backbone.layers.10.mlp.up_proj": true,
+        "model.backbone.layers.10.input_layernorm": false,
+        "model.backbone.layers.10.post_attention_layernorm": false,
+        "model.backbone.layers.11.self_attn.q_proj": true,
+        "model.backbone.layers.11.self_attn.k_proj": true,
+        "model.backbone.layers.11.self_attn.v_proj": true,
+        "model.backbone.layers.11.self_attn.o_proj": true,
+        "model.backbone.layers.11.self_attn.rope": false,
+        "model.backbone.layers.11.mlp.gate_proj": true,
+        "model.backbone.layers.11.mlp.down_proj": true,
+        "model.backbone.layers.11.mlp.up_proj": true,
+        "model.backbone.layers.11.input_layernorm": false,
+        "model.backbone.layers.11.post_attention_layernorm": false,
+        "model.backbone.layers.12.self_attn.q_proj": true,
+        "model.backbone.layers.12.self_attn.k_proj": true,
+        "model.backbone.layers.12.self_attn.v_proj": true,
+        "model.backbone.layers.12.self_attn.o_proj": true,
+        "model.backbone.layers.12.self_attn.rope": false,
+        "model.backbone.layers.12.mlp.gate_proj": true,
+        "model.backbone.layers.12.mlp.down_proj": true,
+        "model.backbone.layers.12.mlp.up_proj": true,
+        "model.backbone.layers.12.input_layernorm": false,
+        "model.backbone.layers.12.post_attention_layernorm": false,
+        "model.backbone.layers.13.self_attn.q_proj": true,
+        "model.backbone.layers.13.self_attn.k_proj": true,
+        "model.backbone.layers.13.self_attn.v_proj": true,
+        "model.backbone.layers.13.self_attn.o_proj": true,
+        "model.backbone.layers.13.self_attn.rope": false,
+        "model.backbone.layers.13.mlp.gate_proj": true,
+        "model.backbone.layers.13.mlp.down_proj": true,
+        "model.backbone.layers.13.mlp.up_proj": true,
+        "model.backbone.layers.13.input_layernorm": false,
+        "model.backbone.layers.13.post_attention_layernorm": false,
+        "model.backbone.layers.14.self_attn.q_proj": true,
+        "model.backbone.layers.14.self_attn.k_proj": true,
+        "model.backbone.layers.14.self_attn.v_proj": true,
+        "model.backbone.layers.14.self_attn.o_proj": true,
+        "model.backbone.layers.14.self_attn.rope": false,
+        "model.backbone.layers.14.mlp.gate_proj": true,
+        "model.backbone.layers.14.mlp.down_proj": true,
+        "model.backbone.layers.14.mlp.up_proj": true,
+        "model.backbone.layers.14.input_layernorm": false,
+        "model.backbone.layers.14.post_attention_layernorm": false,
+        "model.backbone.layers.15.self_attn.q_proj": true,
+        "model.backbone.layers.15.self_attn.k_proj": true,
+        "model.backbone.layers.15.self_attn.v_proj": true,
+        "model.backbone.layers.15.self_attn.o_proj": true,
+        "model.backbone.layers.15.self_attn.rope": false,
+        "model.backbone.layers.15.mlp.gate_proj": true,
+        "model.backbone.layers.15.mlp.down_proj": true,
+        "model.backbone.layers.15.mlp.up_proj": true,
+        "model.backbone.layers.15.input_layernorm": false,
+        "model.backbone.layers.15.post_attention_layernorm": false,
+        "model.backbone.norm": false,
+        "model.decoder.embed_tokens": false,
+        "model.decoder.layers.0.self_attn.q_proj": true,
+        "model.decoder.layers.0.self_attn.k_proj": true,
+        "model.decoder.layers.0.self_attn.v_proj": true,
+        "model.decoder.layers.0.self_attn.o_proj": true,
+        "model.decoder.layers.0.self_attn.rope": false,
+        "model.decoder.layers.0.mlp.gate_proj": true,
+        "model.decoder.layers.0.mlp.down_proj": true,
+        "model.decoder.layers.0.mlp.up_proj": true,
+        "model.decoder.layers.0.input_layernorm": false,
+        "model.decoder.layers.0.post_attention_layernorm": false,
+        "model.decoder.layers.1.self_attn.q_proj": true,
+        "model.decoder.layers.1.self_attn.k_proj": true,
+        "model.decoder.layers.1.self_attn.v_proj": true,
+        "model.decoder.layers.1.self_attn.o_proj": true,
+        "model.decoder.layers.1.self_attn.rope": false,
+        "model.decoder.layers.1.mlp.gate_proj": true,
+        "model.decoder.layers.1.mlp.down_proj": true,
+        "model.decoder.layers.1.mlp.up_proj": true,
+        "model.decoder.layers.1.input_layernorm": false,
+        "model.decoder.layers.1.post_attention_layernorm": false,
+        "model.decoder.layers.2.self_attn.q_proj": true,
+        "model.decoder.layers.2.self_attn.k_proj": true,
+        "model.decoder.layers.2.self_attn.v_proj": true,
+        "model.decoder.layers.2.self_attn.o_proj": true,
+        "model.decoder.layers.2.self_attn.rope": false,
+        "model.decoder.layers.2.mlp.gate_proj": true,
+        "model.decoder.layers.2.mlp.down_proj": true,
+        "model.decoder.layers.2.mlp.up_proj": true,
+        "model.decoder.layers.2.input_layernorm": false,
+        "model.decoder.layers.2.post_attention_layernorm": false,
+        "model.decoder.layers.3.self_attn.q_proj": true,
+        "model.decoder.layers.3.self_attn.k_proj": true,
+        "model.decoder.layers.3.self_attn.v_proj": true,
+        "model.decoder.layers.3.self_attn.o_proj": true,
+        "model.decoder.layers.3.self_attn.rope": false,
+        "model.decoder.layers.3.mlp.gate_proj": true,
+        "model.decoder.layers.3.mlp.down_proj": true,
+        "model.decoder.layers.3.mlp.up_proj": true,
+        "model.decoder.layers.3.input_layernorm": false,
+        "model.decoder.layers.3.post_attention_layernorm": false,
+        "model.decoder.norm": false,
+        "model.text_embeddings": true,
+        "model.audio_embeddings": true,
+        "model.projection": true,
+        "model.codebook0_head": true,
+        "_audio_tokenizer.encoder.init_conv1d.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.0.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.0.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.1.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.1.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.2.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.2.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.encoder.layers.3.residuals.0.streaming_add": false,
+        "_audio_tokenizer.encoder.layers.3.downsample.conv.conv": false,
+        "_audio_tokenizer.encoder.final_conv1d.conv.conv": false,
+        "_audio_tokenizer.decoder.init_conv1d.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.0.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.1.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.1.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.2.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.2.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.layers.3.upsample.convtr.convtr": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.block.0.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.block.1.conv.conv": false,
+        "_audio_tokenizer.decoder.layers.3.residuals.0.streaming_add": false,
+        "_audio_tokenizer.decoder.final_conv1d.conv.conv": false,
+        "_audio_tokenizer.quantizer.rvq_first.input_proj": false,
+        "_audio_tokenizer.quantizer.rvq_first.output_proj": false,
+        "_audio_tokenizer.quantizer.rvq_first.vq.layers.0.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.input_proj": false,
+        "_audio_tokenizer.quantizer.rvq_rest.output_proj": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.0.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.1.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.2.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.3.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.4.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.5.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.6.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.7.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.8.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.9.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.10.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.11.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.12.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.13.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.14.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.15.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.16.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.17.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.18.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.19.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.20.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.21.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.22.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.23.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.24.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.25.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.26.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.27.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.28.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.29.codebook": false,
+        "_audio_tokenizer.quantizer.rvq_rest.vq.layers.30.codebook": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.0.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.1.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.2.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.3.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.4.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.5.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.6.self_attn.rope": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.gating.linear1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.gating.linear2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.norm1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.norm2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.layer_scale_1": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.layer_scale_2": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.in_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.out_proj": false,
+        "_audio_tokenizer.encoder_transformer.transformer.layers.7.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.0.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.1.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.2.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.3.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.4.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.5.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.6.self_attn.rope": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.gating.linear1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.gating.linear2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.norm1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.norm2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.layer_scale_1": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.layer_scale_2": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.in_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.out_proj": false,
+        "_audio_tokenizer.decoder_transformer.transformer.layers.7.self_attn.rope": false,
+        "_audio_tokenizer.downsample.conv.conv.conv": false,
+        "_audio_tokenizer.upsample.convtr.convtr.convtr": false
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "text_vocab_size": 128256,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.51.3",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9dde645c89fa7c541a80f08679e38884c32f5921355e7921f61a93268f1193
+size 1711007798

model.safetensors.index.json

@@ -0,0 +1,482 @@
+{
+    "metadata": {
+        "total_size": 1710950784
+    },
+    "weight_map": {
+        "model.audio_embeddings.biases": "model.safetensors",
+        "model.audio_embeddings.scales": "model.safetensors",
+        "model.audio_embeddings.weight": "model.safetensors",
+        "model.audio_head": "model.safetensors",
+        "model.backbone.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.backbone.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.backbone.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.backbone.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.backbone.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.backbone.norm.weight": "model.safetensors",
+        "model.codebook0_head.biases": "model.safetensors",
+        "model.codebook0_head.scales": "model.safetensors",
+        "model.codebook0_head.weight": "model.safetensors",
+        "model.decoder.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.decoder.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.decoder.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.decoder.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.decoder.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.decoder.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.decoder.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.decoder.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.decoder.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.decoder.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.decoder.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.decoder.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.decoder.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.decoder.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.decoder.norm.weight": "model.safetensors",
+        "model.projection.biases": "model.safetensors",
+        "model.projection.scales": "model.safetensors",
+        "model.projection.weight": "model.safetensors",
+        "model.text_embeddings.biases": "model.safetensors",
+        "model.text_embeddings.scales": "model.safetensors",
+        "model.text_embeddings.weight": "model.safetensors"
+    }
+}