Add files using upload-large-folder tool

Qwen2.5-Coder-32B-Instruct/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

Qwen2.5-Coder-32B-Instruct/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2024 Alibaba Cloud
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

Qwen2.5-Coder-32B-Instruct/model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c03b072b4aad4da68016b75b78c6eb3ea6b35e18ac0dae4906146603fa32e23
+size 4876059416

Qwen2.5-Coder-32B-Instruct/model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5ee9a4665ae7d5c9e6d37f77d93c47244a80ee41284060efde69d223472a87a
+size 4876059416

Qwen2.5-Coder-32B-Instruct/model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49f60205e190369145352de972e3510bcfeef6b5a26041573032edbe132c1e06
+size 4876059416

Qwen2.5-Coder-32B-Instruct/model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a53a0d4a02dcb5f036da4fcd50e408107144ff4c4b09357cf1829be2ef382f9
+size 4876059416

Qwen2.5-Coder-32B-Instruct/model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b26127defc68bff2e0744ae9afc9c8ab1730fee071e0400b4bfe8f07fadda5b
+size 4876059416

Qwen2.5-Coder-32B-Instruct/model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:983ebbded19c19264d08845710c9993714d60e17f81c62e1e15c8f174af79847
+size 2123397800

Qwen2.5-Coder-7B-Instruct/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b6f069918b07c064cbba8ae4f00f529aa9bbf84b7cdfcb7fc2694a40f6aa8ef
+size 4877660776

Qwen2.5-Coder-7B-Instruct/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3d46733e7aa054ea7b063fbccd0a5a08446e7bd1814bef26936c5aa1331da62
+size 4932751008

Qwen2.5-Coder-7B-Instruct/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fe45dacee087385b3d2d6dd27a7413a8a56d95f145772facc148fa86fc73446
+size 4330865200

Qwen2.5-Coder-7B-Instruct/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aa6e5cbe642377fd441fb4e60e83cca96b2bcd9820e245b9ea06d94653f17f2
+size 1089994880

diffuevo/ar_cpt_step4000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3968501c23d5466892466d28ba8eb750f40edb7cc360ced313995facc84d3c7
+size 25811170480

diffuevo/diffuevo_500b.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eccdabe16f344170a3abb392b907eea4a8e5b90086fffa05f50eff69151b5d03
+size 25811170480

evo-1-8k-base/README.md

@@ -0,0 +1,98 @@
+---
+license: apache-2.0
+tags:
+- stripedhyena
+- long context
+- deep signal processing
+- hybrid
+- biology
+- genomics
+---
+
+
+## Evo-1 (Phase 1)
+
+<p align="center">
+<img src="https://cdn-uploads.huggingface.co/production/uploads/62a1306bbe7fa896d2c8de44/JoEHcvLTUlHoMcgh3mmAz.png" width="70%" />
+</p>
+
+
+### News
+
+We identified and fixed an issue related to a wrong permutation of some projections, which affects generation quality. To use the new model revision, please load as follows:
+
+```python
+config = AutoConfig.from_pretrained(model_name, trust_remote_code=True, revision="1.1_fix")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    config=config,
+    trust_remote_code=True,
+    revision="1.1_fix"
+)
+```
+
+### About 
+
+Evo is a biological foundation model capable of long-context modeling and design.
+
+Evo uses the [StripedHyena architecture](https://github.com/togethercomputer/stripedhyena) to enable modeling of sequences at a single-nucleotide, byte-level resolution with near-linear scaling of compute and memory relative to context length.
+Evo has 7 billion parameters and is trained on OpenGenome, a prokaryotic whole-genome dataset containing ~300 billion tokens.
+
+Technical details about Evo can be found in our preprint and our accompanying blog posts. Evo was collaboratively developed by the [Arc Institute](https://arcinstitute.org/) and TogetherAI.
+
+As part of our commitment to open science, we release **weights of 15 intermediate pretraining checkpoints** for phase 1 and phase 2 of pretraining. The checkpoints are available as branches of the corresponding HuggingFace repository.
+
+**Evo-1 (Phase 1)** is our first model in the Evo family, trained at a context length of 8k.
+
+| Checkpoint Name                        | Description |
+|----------------------------------------|-------------|
+| `evo-1-8k-base`     | A model pretrained with 8,192 context. We use this model as the base model for molecular-scale finetuning tasks. |
+| `evo-1-131k-base`   | A model pretrained with 131,072 context using `evo-1-8k-base` as the initialization. We use this model to reason about and generate sequences at the genome scale. |
+
+### Model Architecture
+
+StripedHyena is a deep signal processing, hybrid architecture composed of multi-head attention and gated convolutions arranged in [Hyena](https://arxiv.org/abs/2302.10866) blocks, improving over decoder-only Transformers.  
+
+StripedHyena is designed to leverage the specialization of each of its layer classes, with Hyena layers implementing the bulk of the computation required for sequence processing and attention layers supplementing the ability to perform targeted pattern recall.
+
+Some highlights of the architecture:
+- **Efficient autoregressive generation** via a recurrent mode (>500k generation with a single 80GB GPU)
+- **Significantly faster training and finetuning** at long context (>3x at 131k)
+- **Improved scaling laws over state-of-the-art architectures** (e.g., Transformer++) on both natural language and biological sequences.
+-  **Robust to training beyond the compute-optimal frontier** e.g., training way beyond Chinchilla-optimal token amounts (see preprint for details -- more details to come)
+
+
+### How to use Evo
+
+Example usage is provided in the [standalone repo](https://github.com/evo-design/evo).
+
+
+#### Parametrization for Inference and Finetuning
+
+One of the advantages of deep signal processing models is their flexibility. Different parametrizations of convolutions can be used depending on the memory, expressivity and causality requirements of pretraining, finetuning or inference workloads. 
+
+The main classes are:
+- Modal canonical: unconstrained poles ([reference](https://arxiv.org/pdf/2203.14343.pdf), [reference](https://arxiv.org/abs/2310.18780)), or constrained poles ([reference](https://arxiv.org/abs/2206.11893), [reference](https://arxiv.org/pdf/2303.06349.pdf)).
+- Companion canonical / rational: TBA.
+- Hypernetworks: hypernetwork ([reference](https://arxiv.org/abs/2102.02611)), modulated hypernetwork ([reference](https://arxiv.org/abs/2302.10866)).
+- Explicit: modulated explicit ([reference](https://arxiv.org/pdf/2210.09298.pdf)).
+
+StripedHyena is a mixed precision model. Make sure to keep your `poles` and `residues` in `float32` precision, especially for longer prompts or training.
+
+
+
+### Disclaimer 
+
+To use StripedHyena outside of the playground, you will need to install custom kernels. Please follow the instructions from the [standalone repository](https://github.com/togethercomputer/stripedhyena).
+
+## Cite
+
+```
+@article{nguyen2024sequence,
+   author = {Eric Nguyen and Michael Poli and Matthew G. Durrant and Armin W. Thomas and Brian Kang and Jeremy Sullivan and Madelena Y. Ng and Ashley Lewis and Aman Patel and Aaron Lou and Stefano Ermon and Stephen A. Baccus and Tina Hernandez-Boussard and Christopher Ré and Patrick D. Hsu and Brian L. Hie},
+   journal = {Arc Institute manuscripts},
+   title = {Sequence modeling and design from molecular to genome scale with Evo},
+   url = {https://arcinstitute.org/manuscripts/Evo},
+   year = {2024},
+}
+```

evo-1-8k-base/config.json

@@ -0,0 +1,91 @@
+{
+  "_commit_hash": "cb2b3eb17365b1c22deab9114aec7afb2746c9f1",
+  "_name_or_path": "togethercomputer/evo-1-8k-base",
+  "architectures": [
+    "StripedHyenaModelForCausalLM"
+  ],
+  "attn_layer_idxs": [
+    8,
+    16,
+    24
+  ],
+  "auto_map": {
+    "AutoConfig": "togethercomputer/evo-1-131k-base--configuration_hyena.StripedHyenaConfig",
+    "AutoModelForCausalLM": "togethercomputer/evo-1-131k-base--modeling_hyena.StripedHyenaModelForCausalLM",
+    "AutoTokenizer": [
+      "togethercomputer/evo-1-131k-base--tokenizer.ByteTokenizer",
+      null
+    ]
+  },
+  "column_split": false,
+  "column_split_hyena": true,
+  "eps": 1e-06,
+  "final_norm": true,
+  "hidden_size": 4096,
+  "hyena_filter_groups": 1,
+  "hyena_layer_idxs": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31
+  ],
+  "inference_mode": false,
+  "inner_mlp_size": 10928,
+  "log_intermediate_values": false,
+  "make_vocab_size_divisible_by": 8,
+  "max_seqlen": 8192,
+  "mha_out_proj_bias": true,
+  "mlp_activation": "gelu",
+  "model_parallel_size": 1,
+  "model_type": "stripedhyena",
+  "num_attention_heads": 32,
+  "num_filters": 4096,
+  "num_layers": 32,
+  "pipe_parallel_size": 1,
+  "prefill_style": "fft",
+  "proj_groups": 1,
+  "qkv_proj_bias": true,
+  "rotary_emb_base": 10000,
+  "rotary_emb_scaling_factor": 1,
+  "short_filter_bias": true,
+  "short_filter_length": 3,
+  "smeared_gqa": false,
+  "split_k0": true,
+  "state_size": 8,
+  "tie_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_cache": true,
+  "use_flash_attention_2": true,
+  "use_flash_attn": true,
+  "use_flash_depthwise": false,
+  "use_flash_rmsnorm": false,
+  "use_flashfft": false,
+  "use_interpolated_rotary_pos_emb": false,
+  "vocab_size": 512
+}

evo-1-8k-base/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.40.1"
+}

evo-1-8k-base/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d5b2af1ff0f441a0a39db7fd2047be0a83ef062e5173009c4bc59ce687bac9
+size 4929849248

evo-1-8k-base/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d054d7f3ef4286da9e51045016de044738f4e66da332576f6d292c7965ecc4
+size 3003304856

evo-1-8k-base/model.safetensors.index.json

@@ -0,0 +1,445 @@
+{
+  "metadata": {
+    "total_size": 12913164672
+  },
+  "weight_map": {
+    "backbone.blocks.0.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.0.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.1.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.10.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.11.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.12.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.12.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.12.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.12.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.13.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.13.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.14.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.15.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.inner_mha_cls.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.inner_mha_cls.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.inner_mha_cls.out_proj.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.inner_mha_cls.out_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.inner_mha_cls.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.16.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.17.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.18.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.19.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.2.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.2.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.20.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.20.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.21.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.22.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.filter.D": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.filter.poles": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.filter.residues": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.filter.short_filter_bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.filter.short_filter_weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.mlp.l2.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.mlp.l3.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.out_filter_dense.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.out_filter_dense.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.projections.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.23.projections.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.inner_mha_cls.Wqkv.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.inner_mha_cls.Wqkv.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.inner_mha_cls.out_proj.bias": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.inner_mha_cls.out_proj.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.inner_mha_cls.rotary_emb.inv_freq": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.mlp.l1.weight": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.24.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.24.post_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.24.pre_norm.scale": "model-00002-of-00003.safetensors",
+    "backbone.blocks.25.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.25.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.26.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.27.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.28.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.29.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.3.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.3.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.30.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.30.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.filter.D": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.filter.poles": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.filter.residues": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.filter.short_filter_bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.filter.short_filter_weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.mlp.l1.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.mlp.l2.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.mlp.l3.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.out_filter_dense.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.out_filter_dense.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.post_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.pre_norm.scale": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.projections.bias": "model-00003-of-00003.safetensors",
+    "backbone.blocks.31.projections.weight": "model-00003-of-00003.safetensors",
+    "backbone.blocks.4.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.4.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.5.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.6.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.7.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.inner_mha_cls.Wqkv.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.inner_mha_cls.Wqkv.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.inner_mha_cls.out_proj.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.inner_mha_cls.out_proj.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.inner_mha_cls.rotary_emb.inv_freq": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.8.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.filter.D": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.filter.poles": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.filter.residues": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.filter.short_filter_bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.filter.short_filter_weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.mlp.l1.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.mlp.l2.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.mlp.l3.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.out_filter_dense.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.out_filter_dense.weight": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.post_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.pre_norm.scale": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.projections.bias": "model-00001-of-00003.safetensors",
+    "backbone.blocks.9.projections.weight": "model-00001-of-00003.safetensors",
+    "backbone.embedding_layer.weight": "model-00001-of-00003.safetensors",
+    "backbone.norm.scale": "model-00001-of-00003.safetensors"
+  }
+}