Add files using upload-large-folder tool

.gitattributes

@@ -1,35 +1 @@
-*.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

LICENSE

@@ -0,0 +1,201 @@
+                                 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 2017 Johns Hopkins University (Shinji Watanabe)
+
+   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.

MANIFEST.json

@@ -0,0 +1,28 @@
+{
+  "artifact": "espnet/bagpiper-sft",
+  "format": "native ESPnet weight-only checkpoint",
+  "weight_file": {
+    "path": "model.pt",
+    "bytes": 18188823609,
+    "sha256": "50980756fad38bbefeb326ac0012e39f431ec5af8c0caaac8bd254f179f33746",
+    "top_level_keys": ["module"],
+    "tensor_count": 1382
+  },
+  "source": {
+    "repo": "JinchuanTian/bagpiper_sft",
+    "repo_type": "dataset",
+    "revision": "b11d5a0c11ad488edd04e3734d4bdff764977f57",
+    "path": "exp/opuslm_v2_stage2_pretrain_base/checkpoints/step_270000/global_step269985/mp_rank_00_model_states.pt",
+    "bytes": 18188293839,
+    "sha256": "e0d8fdd57c8cb8c938cd61ada43b20e469d9cea33ad8450e0971f80d4f9667b6"
+  },
+  "validation": {
+    "source_tensors_equal": 1381,
+    "added_tensor": "vocab_weight",
+    "strict_load": "pass",
+    "espnet_revision": "1992821bfb6d68c6636d1b75340b8b2b591bc015",
+    "transformers": "5.5.4",
+    "pytorch": "2.12.1+cu129",
+    "gpu": "NVIDIA H100 80GB HBM3"
+  }
+}

README.md

@@ -0,0 +1,128 @@
+---
+library_name: espnet
+pipeline_tag: any-to-any
+base_model: espnet/bagpiper
+language:
+- en
+tags:
+- audio
+- multimodal
+- speech-language-model
+- audio-understanding
+- audio-generation
+- text-to-audio
+- espnet
+- pytorch
+inference: false
+---
+
+# Bagpiper SFT
+
+Bagpiper is an 8B audio foundation model for open-ended audio understanding and
+generation through rich captions. It accepts text and audio and can return text
+or generate speech, music, environmental sounds, and mixtures of them.
+
+This repository contains the paper-selected general-SFT checkpoint from
+[Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions](https://arxiv.org/abs/2602.05220).
+
+## Files and format
+
+- `model.pt`: native ESPnet weight-only checkpoint, stored as
+  `{"module": state_dict}`.
+- `train.yaml`: checkpoint-compatible model configuration.
+- `inference_text.yaml`: audio-understanding/text-output decoding.
+- `inference_audio.yaml`: text-then-audio generation decoding.
+- `deepspeed.json`: optional fine-tuning configuration.
+- `MANIFEST.json` and `SHA256SUMS`: provenance and integrity records.
+
+`model.pt` contains 1,382 tensors: the 1,381 BF16 tensors from training plus the
+deterministically reconstructed FP32 `vocab_weight` buffer required by the current
+strict ESPnet loader. It contains no optimizer or exact-resume state. It is not a
+Transformers `from_pretrained` directory and no vLLM compatibility is claimed.
+
+## Download
+
+```bash
+hf download espnet/bagpiper-sft --local-dir bagpiper-sft
+sha256sum -c bagpiper-sft/SHA256SUMS
+```
+
+## ESPnet runtime
+
+The release was strict-loaded with:
+
+- ESPnet PR [#6503](https://github.com/espnet/espnet/pull/6503), commit
+  `1992821bfb6d68c6636d1b75340b8b2b591bc015`;
+- Python 3.11.15, PyTorch 2.12.1+cu129, Transformers 5.5.4;
+- FlashAttention-3 3.0.0 at source commit
+  `77aacb68d194ba9af1010eda5eac3e7c0df8e6f6`; and
+- one NVIDIA H100 80GB HBM3.
+
+```bash
+git clone --branch titan-pt-weightonly-init https://github.com/jctian98/espnet.git
+cd espnet
+git checkout 1992821bfb6d68c6636d1b75340b8b2b591bc015
+python -m pip install -e '.[speechlm]'
+python -m pip install --no-build-isolation \
+  'flash-attn-3 @ git+https://github.com/Dao-AILab/flash-attention.git@77aacb68d194ba9af1010eda5eac3e7c0df8e6f6#subdirectory=hopper'
+```
+
+Use `espnet2/speechlm/bin/inference.py` with `train.yaml`, one of the supplied
+inference YAMLs, and `model.pt`. The checkpoint can also initialize compatible
+fine-tuning through `espnet2/speechlm/bin/train.py --resume-path model.pt`; this
+starts a fresh optimizer, scheduler, and step counter.
+
+## Paper-reported results
+
+These values are from the paper's checkpoint and evaluation protocols; they were
+not rerun as part of the Hub upload.
+
+| Evaluation | Result |
+|---|---:|
+| LibriSpeech test-clean WER | 2.5 |
+| MMAU-Mini | 74.5 |
+| MMAU | 73.1 |
+| MMAR | 57.0 |
+| AIR-Bench chat | 6.57 |
+| AudioBench aggregate | 70.39 |
+| General-model TTS WER | 2.7 |
+
+The paper reports audio-fingerprint overlap between the SFT pool and **12.8% of
+AudioBench** and **3.2% of AIR-Bench** evaluation clips. Interpret those results
+with this disclosure.
+
+## Provenance and validation
+
+- Selected checkpoint: `step_270000/global_step269985`.
+- Raw source: `JinchuanTian/bagpiper_sft` at revision
+  `b11d5a0c11ad488edd04e3734d4bdff764977f57`.
+- Raw SHA-256: `e0d8fdd57c8cb8c938cd61ada43b20e469d9cea33ad8450e0971f80d4f9667b6`.
+- `model.pt` SHA-256:
+  `50980756fad38bbefeb326ac0012e39f431ec5af8c0caaac8bd254f179f33746`.
+- All 1,381 source tensors matched the converted file exactly with
+  `torch.equal`; the only added key was `vocab_weight`.
+- The 1,382-entry state dict passed the native ESPnet strict inference loader.
+
+## Limitations and responsible use
+
+Understanding can hallucinate or mistranscribe. Generated audio can contain
+artifacts, wrong words, unsafe content, or unintended resemblance to people and
+styles. Most reported evaluations are English and some rely on model judges. The
+model has no built-in watermark, factuality verifier, copyright filter, or
+speaker-consent check. Do not use it for impersonation, deceptive media,
+surveillance, biometric authentication, or high-stakes automated decisions.
+
+Training-data availability and terms are documented at
+[Bagpiper SFT Data](https://huggingface.co/datasets/espnet/Bagpiper_SFT_Data).
+Third-party component terms are listed in `THIRD_PARTY_NOTICES.md`.
+
+## Citation
+
+```bibtex
+@article{tian2026bagpiper,
+  title={Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions},
+  author={Tian, Jinchuan and Wang, Haoran and Su, Bo-Hao and others},
+  journal={arXiv preprint arXiv:2602.05220},
+  year={2026}
+}
+```

SHA256SUMS

@@ -0,0 +1,9 @@
+7f04d858ce14079bac4bc150278cbbd321f21512204953cc3e2db58a84a18fab  README.md
+4696c3c9551da6fef1368be1e4ed2c80cf13e55448c6dcf2aba9462f5ff29ef5  LICENSE
+13e4484dd105cfc77a8fc41a1adc51869e381f70b6afeeb5469f5b75da80f3fb  THIRD_PARTY_NOTICES.md
+7bf054db4d438bb66d4e3e6c0601b12bbed3e537d51305c8f7c4d9e2830604f0  MANIFEST.json
+38f04f7fc323963ee9cbff09167d60905e2c80d4d17a58fe7e5fa62b86321ae8  train.yaml
+3f8dddd19ba6de3d63bc5a82912955411b3b38c0a0880b21ddd2a0e210507212  deepspeed.json
+260c0dda42134194e480666d1f4cafb1d3ffd3b2ffeaf0af06ad9d1a21e3384a  inference_audio.yaml
+66f59b0a0da7e5ecf67dd15075ee297572873de84836c834cce305c1cb176362  inference_text.yaml
+50980756fad38bbefeb326ac0012e39f431ec5af8c0caaac8bd254f179f33746  model.pt

THIRD_PARTY_NOTICES.md

@@ -0,0 +1,40 @@
+# Third-party notices
+
+`model.pt` contains parameters initialized from or associated with these components:
+
+- Qwen3-8B-Base, revision `49e3418fbbbca6ecbdf9608b4d22e5a407081db4`, Apache-2.0:
+  https://huggingface.co/Qwen/Qwen3-8B-Base
+- Qwen3-Omni-30B-A3B-Instruct audio encoder, revision
+  `26291f793822fb6be9555850f06dfe95f2d7e695`, Apache-2.0:
+  https://huggingface.co/Qwen/Qwen3-Omni-30B-A3B-Instruct
+- X-Codec general-audio codec, revision
+  `240735a1ade315cb9b22604fe898e7df03d67378`, MIT:
+  https://huggingface.co/hf-audio/xcodec-hubert-general
+- ESPnet SpeechLM code and release configuration, Apache-2.0:
+  https://github.com/espnet/espnet
+
+Upstream names and trademarks do not imply endorsement.
+
+## X-Codec MIT notice
+
+MIT License
+
+Copyright (c) 2025 YE Zhen
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

deepspeed.json

@@ -0,0 +1,45 @@
+{
+  "train_micro_batch_size_per_gpu": 1,
+  "gradient_accumulation_steps": 1,
+  "gradient_clipping": 1.0,
+  "bf16": {"enabled": true},
+  "checkpoint": {"load_universal": true},
+  "optimizer": {
+    "type": "Adam",
+    "params": {
+      "lr": 0.00001,
+      "betas": [0.9, 0.95],
+      "eps": 1e-8,
+      "weight_decay": 3e-7,
+      "adam_w_mode": true
+    }
+  },
+  "zero_optimization": {
+    "stage": 1,
+    "allgather_partitions": true,
+    "allgather_bucket_size": 300000000,
+    "reduce_scatter": true,
+    "reduce_bucket_size": 300000000,
+    "overlap_comm": true,
+    "contiguous_gradients": true
+  },
+  "activation_checkpointing": {
+    "partition_activations": false,
+    "cpu_checkpointing": false,
+    "contiguous_memory_optimization": true,
+    "number_checkpoints": null,
+    "synchronize_checkpoint_boundary": false,
+    "profile": false
+  },
+  "scheduler": {
+    "type": "WarmupCosineLR",
+    "params": {
+      "warmup_type": "linear",
+      "total_num_steps": 600000,
+      "warmup_num_steps": 350000,
+      "cos_min_ratio": 1.0
+    }
+  },
+  "wall_clock_breakdown": false,
+  "steps_per_print": 1000
+}

inference_audio.yaml

@@ -0,0 +1,17 @@
+dtype: bfloat16
+num_hypo: 1
+enforce_modality: ["text", "audio"]
+
+audio:
+  temperature: 0.8
+  topk: 20
+  cfg: 3
+  max_step: 2048
+  min_step: 50
+
+text:
+  temperature: 0.6
+  topk: 20
+  cfg: 1
+  max_step: 2048
+  min_step: 1

inference_text.yaml

@@ -0,0 +1,17 @@
+dtype: bfloat16
+num_hypo: 1
+enforce_modality: ["text"]
+
+audio:
+  temperature: 0.8
+  topk: 20
+  cfg: 3
+  max_step: 2048
+  min_step: 50
+
+text:
+  temperature: 0.6
+  topk: 20
+  cfg: 1
+  max_step: 2048
+  min_step: 1

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50980756fad38bbefeb326ac0012e39f431ec5af8c0caaac8bd254f179f33746
+size 18188823609

train.yaml

@@ -0,0 +1,45 @@
+job_type: speechlm
+
+multimodal_io:
+    text:
+        tokenizer_name: Qwen/Qwen3-8B-Base
+    discrete_audio:
+        codec_choice: Xcodec
+        codec_hf_model_tag: hf-audio/xcodec-hubert-general
+        ssl_choice: null
+        ssl_hf_model_tag: null
+        delay_interleave: true
+        stream_weights: [0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125]
+    continuous_audio:
+        encoder_choice: huggingface
+        encoder_hf_model_tag: Qwen/Qwen3-Omni-30B-A3B-Instruct
+        attn_implementation: flash_attention_3
+        dtype: bfloat16
+
+model:
+    model_choice: parallel
+    model_hf_tag: Qwen/Qwen3-8B-Base
+    model_conf:
+        attn_implementation: flash_attention_3
+        dtype: bfloat16
+    activation_checkpointing: true
+
+preprocessor:
+    audio_input: continuous_audio
+    audio_output: discrete_audio
+    loss_region: assistant
+    audio_cfg: 0.05
+
+data_loading:
+    batchfy_method: pack
+    batch_size: 20000
+    save_loader_state: false
+    seed: 43
+    num_workers: 6
+
+trainer:
+    deepspeed_config: deepspeed.json
+    freeze_param: [multimodal_io_dict.discrete_audio, multimodal_io_dict.continuous_audio]
+    max_step: 700000
+    save_interval: 2500
+    log_interval: 1