Confucius4-R2T2 converted for Core ML on the Apple Neural Engine (encoder fp16, decoder LUT8 with 128-row prefill and verify head)

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

LICENSE-Qwen3-ASR.txt

@@ -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 [yyyy] [name of copyright owner]
+
+   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.

MODEL_LICENSE

@@ -0,0 +1,62 @@
+NetEase Youdao Model Use License Agreement
+
+By clicking “I agree” to this NetEase Youdao Model Use License Agreement (“this Agreement”) , or by otherwise using any portion or element of the Model or any Derivative Work, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately. If you do not agree to this Agreement, you must immediately cease all use and permanently delete the Model and any Derivative Works.
+
+1. Definitions
+1.1 “This Agreement”: means the NetEase Youdao Model Use License Agreement, including all of its terms and conditions.
+1.2 “We”, “us”, or “our”: means NetEase Youdao , the original right-holder of the Model.
+1.3 “You”: means any natural person or legal entity exercising rights granted by this Agreement and/or using the Model for any purpose and in any field of use.
+1.4 “Model”: means the artificial-intelligence model named “NetEase Youdao Confucius4-R2T2, including but not limited to model weights and final code, in each case only to the extent that such components are published by us at https://github.com/netease-youdao/Confucius4-R2T2.
+1.5 “Derivative Work”: means any derivative of the Model, including without limitation:
+ (i) any modification of the Model, model outputs, or their derivatives;
+ (ii) any work based on the Model, model outputs, or their derivatives; 
+ (iii) any other machine learning model which is created by re-training, fine-tuning, quantizing, LoRA, parameter-efficient fine-tuning, or any other method involving incremental weights or merged checkpoints, in each case based on the Model, model outputs, or their derivatives.
+1.6 “Use”: means downloading, copying, training, modifying, creating Derivative Works, distributing, publishing, running, fine-tuning, publicly displaying, communicating to the public, or otherwise exploiting the Model or any Derivative Work.
+
+2. Scope of License and Restrictions
+2.1 Subject to the terms and conditions of this Agreement, we grant you a worldwide, non-exclusive, non-transferable, royalty-free limited license to Use the Model or any Derivative Work based on the intellectual properties or other rights owned by Us embodied in the Model or any Derivative Work.
+2.2 If You intend to Use, or have already Used, the Model or any Derivative Work, and either (i) your or any of your Affiliates’ products or services had more than 100 million monthly active users in the immediately preceding calendar month, or (ii) your or any of your Affiliates’ annual revenue in the immediately preceding calendar year exceeded RMB 1 billion, You must request a separated license from us, which We may grant to You in our sole discretion. You are not authorized to exercise any of the rights under this Agreement unless and until We have expressly granted You such rights in writing.
+2.3 Commercial Licensing Application Channel
+Department: Youdao Zhiyun Business Team
+Tel: 010-8255-8901
+Email: AIcloud_Business@corp.youdao.com
+Address: NetEase (Beijing) Co., Ltd., Building 7, West District, Zhongguancun Software Park Phase II, No. 10 Xibeiwang East Road, Haidian District, Beijing, China
+2.4 This Agreement is an open-source license for the Model in which we possess intellectual properties and other rights. It governs your Use of the Model only and does not limit any rights that we have regarding the Model.
+
+3. Disclaimer and Risk Allocation
+3.1 The Model and any outputs generated thereby are provided “AS IS,” without warranty of any kind, express or implied, including but not limited to warranties of merchantability, fitness for a particular purpose, non-infringement, absence of errors or omissions, continuity, accuracy, reliability, or stability. You are solely responsible for determining the appropriateness of using or redistributing the Model and assume all risks associated with exercising any rights granted under this Agreement.
+3.2 You shall bear sole responsibility for any infringement, illegality, breach of contract, damages, fines, regulatory investigations, or other liabilities (including, without limitation, infringement of third-party patents, copyrights, trademarks, trade secrets, personality rights, data-protection rights, or any other rights) arising out of or related to your Use of the Model or any outputs generated thereby. We assume no joint, several, supplementary, or advance payment liability.
+3.3 Under no circumstances shall we be liable to you or any third party for any direct, indirect, incidental, special, punitive, or consequential damages (including, without limitation, loss of data, business interruption, or loss of profits) arising out of or related to the Use of the Model, even if we have been advised of the possibility of such damages.
+3.4 Additional Obligations for You and Downstream Recipients
+a) You must ensure that any downstream recipient of the Model or any Derivative Work that you distribute complies with this Agreement, and you must impose appropriate contractual terms on such downstream recipients. If any downstream recipient breaches this Agreement, you shall be responsible for the consequences thereof.
+b) You must retain all original copyright notices and a copy of this Agreement in every copy of the Model or any Derivative Work that you Use.
+c) You may not Use the NetEase Youdao Confucius4-R2T2 or any Derivative Work to improve any AI model, except for the NetEase Youdao Confucius4-R2T2 itself, its Derivative Works，or non-commercial AI models.
+
+4. Compliance Obligations
+4.1 Usage Restrictions
+a) If you distribute a Derivative Work, you must clearly state in the distribution page or accompanying documentation: “Any modifications made to the original model in this Derivative Work are not endorsed, warranted, or guaranteed by the original right-holder of the original model, and the original right-holder disclaims all liability related to this Derivative Work.”
+b) If your Use of the Model or any Derivative Work incorporates any third-party data or weights, you must obtain all necessary authorizations on your own and bear full responsibility for compliance.
+c) You may not Use the Model or any Derivative Work for any purpose that violates the laws or regulatory requirements of the jurisdiction where the outputs and/or the Model are generated or used (including, without limitation, generating false information, discriminatory content, or content that infringes privacy).
+d) If the Model or any Derivative Work is capable of generating content, you must ensure that such content does not violate the laws or regulatory requirements of the applicable jurisdiction (including, without limitation, generating false information, discriminatory content, or content that infringes privacy).
+4.2 Prohibited High-Risk Use
+You must ensure that the Model and any Derivative Work are not deployed, directly or indirectly, in high-risk scenarios such as medical diagnosis, autonomous driving, military applications, critical-infrastructure control, large-scale biometric surveillance, or automated decision-making (e.g., credit or employment evaluations). If you insist on such deployment, you must independently complete all compliance obligations under applicable laws and regulations (including but not limited to GDPR, CCPA, HIPAA, export-control laws, and AI-specific regulations), and we shall bear no liability for any consequences arising therefrom.
+4.3 Infringement Liability
+Should any third party raise claims against you with respect to any Derivative Work you develop or your Use of the Model or any Derivative Work, you shall bear full and independent responsibility for defending against and resolving such claims. If your actions cause us to incur any third-party claims, administrative penalties, or other losses, you shall indemnify us for all losses we thereby suffer, including but not limited to attorney fees, litigation costs, damages, and fines, and shall take all necessary measures to eliminate any adverse impact on us.
+
+5. Reserved Rights
+5.1 We reserve the right to revoke the license granted to you under this Agreement in the event of your breach. Upon revocation, you must immediately cease all Use and permanently delete all copies of the Model and any Derivative Work. Sections 3 and 6 of this Agreement shall survive termination of this Agreement under this circumstance.
+5.2 Nothing in this Agreement grants you any right to use our trade names, trademarks, service marks, or product names, except as reasonably and customarily required to describe the origin of the Model or any Derivative Work—such as reproducing the content of a NOTICE file under Section 3.4 of this Agreement.
+5.3 If you or any of your Affiliates institutes or participates in any legal proceeding (including any cross-claim or counterclaim in a lawsuit) against us or any of our Affiliates, alleging that the Model or any output or any portion thereof infringes any intellectual property or other rights that you own or control, all licenses granted to you under this Agreement shall terminate automatically as of the date such proceeding is filed.
+
+6. Governing Law and Dispute Resolution
+6.1 This Agreement shall be governed by and construed in accordance with the laws of the People’s Republic of China.
+6.2 In the event of any dispute arising out of or in connection with this Agreement, the parties shall first attempt to resolve such dispute through friendly negotiation. If negotiation fails, the parties agree that the dispute shall be arbitrated by the China International Economic and Trade Arbitration Commission ("CIETAC") in Beijing, China, in accordance with CIETAC's arbitration rules then in effect and applicable law, and shall be heard by three (3) arbitrators. The arbitration award shall be final and binding on both parties. The prevailing party shall be entitled to recover reasonable costs, including notarization and investigation fees, arbitration costs, attorneys’ fees, and travel expenses.
+
+7. Severability
+If any provision of this Agreement is held to be invalid or unenforceable, the remaining provisions shall remain in full force and effect. The invalid or unenforceable provision shall be replaced with a valid and enforceable provision that, to the maximum extent permitted by law, most closely reflects the original intent of the invalid or unenforceable provision.
+
+8. Version Updates
+We may release new versions of the AI Model Use License Agreement. Any new version will apply only to Uses occurring after the date of its release. If you obtained the Model under an earlier version, the new version will not have retroactive effect; nevertheless, you are encouraged to adopt the new version voluntarily.
+
+9. Language Version
+In the event of any discrepancy or conflict between the English-language version set forth above and the Chinese-language version of this NetEase Youdao Model Use License Agreement, the Chinese-language version shall prevail for all purposes and shall govern the rights and obligations of the parties.

NOTICE

@@ -0,0 +1,32 @@
+Confucius4-R2T2, Core ML / Apple Neural Engine conversion
+==========================================================
+
+This is a Derivative Work of the NetEase Youdao Confucius4-R2T2 model.
+
+Original model
+  NetEase Youdao Confucius4-R2T2
+  Copyright (c) NetEase Youdao. All rights reserved.
+  https://huggingface.co/netease-youdao/Confucius4-R2T2
+  https://github.com/netease-youdao/Confucius4-R2T2
+  Released under the NetEase Youdao Model Use License Agreement (see MODEL_LICENSE).
+
+Base model
+  Qwen3-ASR-1.7B, Copyright (c) Alibaba Cloud.
+  https://huggingface.co/Qwen/Qwen3-ASR-1.7B
+  Released under the Apache License, Version 2.0 (see LICENSE-Qwen3-ASR.txt).
+  The tokenizer files (tokenizer.json, tokenizer_config.json) are those of the original model.
+
+This conversion
+  The weights in this repository are the original Confucius4-R2T2 weights converted for Core ML on
+  Apple silicon: the audio encoder in fp16, the text decoder palettised to 8 bits (LUT8) in two
+  stateful chunks, and the language-model head palettised to 8 bits. No re-training or fine-tuning
+  was performed. The conversion pipeline and the runtime that drives these files are published with
+  the VoiceInk fork that uses them (GPL-3.0, like VoiceInk).
+
+Any modifications made to the original model in this Derivative Work are not endorsed, warranted,
+or guaranteed by the original right-holder of the original model, and the original right-holder
+disclaims all liability related to this Derivative Work.
+
+Use of these files constitutes acceptance of the NetEase Youdao Model Use License Agreement
+(MODEL_LICENSE). Anyone redistributing these files, or any further derivative, must keep this
+NOTICE and the MODEL_LICENSE with every copy.

R2T2AudioEncoder.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cecce3e737a2f11e9dc4a9016e4e8c559828fe0e4eeb318934f8255fa0d0fa32
+size 243

R2T2AudioEncoder.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407519b071466ab084c6a8624f0277874bdc7d33984aa50f0b117a5ac38f9a9d
+size 415

R2T2AudioEncoder.mlmodelc/metadata.json

@@ -0,0 +1,86 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "storagePrecision" : "Mixed (Float16, Int32)",
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 2048 × 1 × 104)",
+        "shortDescription" : "",
+        "shape" : "[1, 2048, 1, 104]",
+        "name" : "audio_embeds",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "specificationVersion" : 9,
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.batchNorm" : 49,
+      "Ios18.conv" : 150,
+      "Ios18.sub" : 49,
+      "Ios18.matmul" : 384,
+      "Ios18.concat" : 24,
+      "Ios18.rsqrt" : 49,
+      "Ios18.add" : 538,
+      "Ios16.einsum" : 384,
+      "Ios18.tanh" : 28,
+      "Ios16.reduceMean" : 98,
+      "Ios18.pow" : 49,
+      "Ios18.transpose" : 1155,
+      "Ios18.softmax" : 384,
+      "Ios18.reshape" : 1156,
+      "Split" : 72,
+      "Ios18.mul" : 217
+    },
+    "computePrecision" : "Mixed (Float16, Float32, Int32)",
+    "isUpdatable" : "0",
+    "stateSchema" : [
+
+    ],
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    },
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.conversion_date" : "2026-09-20",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 128 × 800)",
+        "shortDescription" : "",
+        "shape" : "[1, 128, 800]",
+        "name" : "input_features",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 104)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 104]",
+        "name" : "key_bias",
+        "type" : "MultiArray"
+      }
+    ],
+    "generatedClassName" : "R2T2AudioEncoder",
+    "method" : "predict"
+  }
+]

R2T2AudioEncoder.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e004c2e3c91144a7227bf347d129af836917cead9740c276ba50e32163ebf4
+size 635020608

README.md

@@ -0,0 +1,157 @@
+---
+license: other
+license_name: netease-model-use-license-agreement
+license_link: https://raw.githubusercontent.com/netease-youdao/Confucius4-R2T2/refs/heads/master/MODEL_LICENSE
+base_model: netease-youdao/Confucius4-R2T2
+pipeline_tag: automatic-speech-recognition
+library_name: coreml
+tags:
+- coreml
+- apple-neural-engine
+- apple-silicon
+- asr
+- speech-recognition
+- streaming
+- real-time
+- qwen3-asr
+- confucius4
+- r2t2
+language:
+- en
+- pt
+- zh
+- es
+- fr
+- de
+- it
+- ja
+- ko
+- ru
+---
+
+# Confucius4-R2T2 for Core ML and the Apple Neural Engine
+
+> Any modifications made to the original model in this Derivative Work are not endorsed, warranted,
+> or guaranteed by the original right-holder of the original model, and the original right-holder
+> disclaims all liability related to this Derivative Work.
+
+This is [NetEase Youdao's Confucius4-R2T2](https://huggingface.co/netease-youdao/Confucius4-R2T2)
+(a real-time speech-recognition fine-tune of Qwen3-ASR-1.7B, 30 languages) converted to Core ML
+programs that run almost entirely on the Apple Neural Engine: every op of the encoder, 99 % of the
+decoder's, and the head's, with the single-row argmax and a dozen index ops per decoder function on
+the CPU. No re-training or fine-tuning was done; the weights are the original ones, converted and
+palettised.
+
+It is the model used by the R2T2 provider in a fork of [VoiceInk](https://github.com/Beingpax/VoiceInk),
+whose runtime and conversion pipeline are published with that fork. The files here are not a
+general-purpose Core ML model with a single input and output: the decoder is a stateful,
+multifunction program that the runtime drives one pass at a time (see *How it is run*).
+
+## Contents
+
+| file | what | size |
+|---|---|---|
+| `R2T2AudioEncoder.mlmodelc` | audio encoder, fp16, one fixed 800-frame (8 s) mel window with a key mask → 104 rows | 607 MB |
+| `r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc` | decoder layers 0–13, LUT8, functions `prefill` (128 rows) and `infer` (1 row), stateful KV cache | 692 MB |
+| `r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc` | decoder layers 14–27 + final norm, same functions | 692 MB |
+| `r2t2_lm_head_lut8.mlmodelc` | language-model head, LUT8, 16-way split: `infer` (one row → logits) and `verify` (128 rows → 128 argmaxes) | 306 MB |
+| `embed_tokens.f16.bin` | token embedding table, fp16, 151 936 × 2048, memory-mapped by the runtime | 622 MB |
+| `tokenizer.json`, `tokenizer_config.json` | the original tokenizer | 11 MB |
+| `MODEL_LICENSE`, `LICENSE-Qwen3-ASR.txt`, `NOTICE`, `SHA256SUMS` | licences, attribution, checksums | |
+
+Requirements: Apple silicon and macOS 15 or later (the decoder uses Core ML stateful models).
+While loaded, the Neural Engine holds the weights dequantised to fp16, about 4.5 GB, outside the
+process; the process itself uses about 200 MB. The first load by a given application compiles the
+programs for the Neural Engine, which takes about 50 s; the compiled programs are cached per
+application binary, so later loads take about a second, and a rebuilt or updated application pays
+the compile once more. The cache also needs free disk: with a nearly full disk (under ~20 GB) every
+load recompiled.
+
+## Interface
+
+The files are meant for a runtime that drives them; they are not a drop-in `MLModel` with audio in
+and text out.
+
+- **Encoder** `R2T2AudioEncoder.mlmodelc`: input `[1, 128, 800]` log-mel frames (Whisper's recipe:
+  16 kHz, n_fft 400, hop 160, Slaney filterbank, `log10`, clamped to 8 dB below the buffer's maximum,
+  `(x + 4) / 4`) plus a key mask for windows shorter than 800 frames (masked keys get −10 000);
+  output `[1, 104, 2048]` rows, 13 per 100 frames.
+- **Decoder chunks**: functions `prefill` (B = 128) and `infer` (B = 1) with inputs
+  `hidden_states [1, B, 2048]` fp16, `position_ids [B]` int32, `causal_mask [1, 1, B, 1024]` fp16
+  (0 to attend, −10 000 otherwise), `current_pos [1]` int32; output `output_hidden_states [1, B, 2048]`
+  (chunk 2's is final-normalised). Both chunks share one `MLState` of shape `(56, 8, 1024, 128)` fp16:
+  layer *l* of chunk *c* uses slots *l* (K) and *28 + l* (V). Rows are written by absolute position,
+  so a caller can rewind and overwrite. Context length 1024.
+- **Head**: `infer` takes `hidden_states [1, 1, 2048]` and returns `logits1…logits16`, each
+  `[1, 1, 9496]` (the vocabulary of 151 936 in 16 slices); `verify` takes `[1, 128, 2048]` and returns
+  per row and per slice `argmax_val`, `argmax_hi`, `argmax_lo` (`[128, 16]` fp16 each), the slice's
+  best logit and its index as `hi × 64 + lo`, exact in fp16.
+- **Embeddings** `embed_tokens.f16.bin`: 151 936 rows of 2048 fp16 values, row-major, no header.
+- The decoder programs load under `.cpuAndNeuralEngine` only: `.all` and `.cpuAndGPU` fail to
+  compile, and `.cpuOnly` cannot load the multifunction packages. Python `coremltools` cannot open
+  the combined packages either; drive them from Swift or Objective-C.
+
+## Accuracy
+
+Word error rate of this conversion, decoding whole utterances, on 100-utterance subsets:
+
+| corpus | this conversion |
+|---|---|
+| LibriSpeech test-clean (English) | 2.40 % |
+| FLEURS pt_br (Brazilian Portuguese) | 3.50 % |
+
+Against the unconverted BF16 weights run on MLX, paired on 300 utterances of each corpus, the
+conversion measured 2.47 % vs 2.42 % (ratio 1.02, 95 % CI 0.96–1.10) on LibriSpeech and
+4.01 % vs 4.01 % (ratio 1.00, CI 0.95–1.05) on FLEURS. The streaming runtime described below ends
+on the same transcript as the whole-file decode.
+
+## How it is run
+
+The runtime that uses these files decodes the whole current piece of audio (up to 30 s) on every
+pass, so the live text converges on the same result as an offline decode. What keeps that cheap
+is what stays in the decoder's KV state between passes: the prompt prefix and the rows of every
+completed encoder window. A pass encodes the partial last window, prefills the new audio rows,
+the prompt scaffold and the previous pass's tokens as a draft, checks the draft with one call of
+the head's `verify` function, and decodes one token at a time only from the first divergence.
+Passes take about 150–250 ms on an M5 Pro; a 30 s piece decodes offline in about 2.5 s
+(20 ms per token).
+
+The prompt is the Qwen3-ASR chat template: system text (hotwords may go here), the user turn with
+`<|audio_start|>`, the encoder's output rows in place of the `<|audio_pad|>` token embeddings,
+`<|audio_end|>`, and the assistant turn, optionally prefixed with `language <Name><asr_text>` to
+force a language. The model answers `language <Name><asr_text>` followed by the text; `|` marks
+where it stops trusting its own output.
+
+## Conversion
+
+Encoder: fp16, the network rewritten in the layout the Neural Engine compiler keeps resident
+(the fused `gelu` op replaced by a tanh formulation, because its constant absolute error is large
+against this encoder's small activations), fixed 800-frame window with a key mask for shorter
+input; 4786/4786 ops on the Neural Engine, 55 dB SNR against the PyTorch encoder.
+
+Decoder: through [ANEMLL](https://github.com/Anemll/Anemll) (patched to return the normalised
+hidden states of every prefill row), two chunks, context 1024, 8-bit palettised weights, a
+128-row `prefill` and a 1-row `infer` function sharing one KV state; prefill and single-step paths
+agree to cosine 1.0. A 6-bit build was measured and rejected (WER ratio 1.16 on Portuguese).
+
+Head: the 16-way split head of the original conversion plus a `verify` function that returns the
+argmax of 128 hidden rows in one call, computed exactly on the Neural Engine.
+
+## Licence
+
+Dual licensing, as for the original model:
+
+- **Weights** (everything in this repository derived from the model): the
+  [NetEase Youdao Model Use License Agreement](MODEL_LICENSE). Using these files means accepting
+  it. In short: royalty-free use including commercial use, with a separate licence required above
+  100 million monthly active users or RMB 1 billion in annual revenue; no use to improve other AI
+  models; no high-risk deployments; keep the NOTICE and MODEL_LICENSE with every copy; anyone you
+  redistribute to is bound by the same terms. The Chinese version of the agreement prevails.
+- **Base model** Qwen3-ASR-1.7B: Apache License 2.0 ([LICENSE-Qwen3-ASR.txt](LICENSE-Qwen3-ASR.txt)).
+- **Conversion pipeline and runtime code**: part of the VoiceInk fork, which is GPL-3.0 like
+  VoiceInk itself. Nothing in this repository is code.
+
+## Attribution
+
+Confucius4-R2T2 by NetEase Youdao. Qwen3-ASR by Alibaba Cloud. Core ML conversion tooling built on
+ANEMLL and coremltools. See [NOTICE](NOTICE).

SHA256SUMS

@@ -0,0 +1,7 @@
+0499602714160467f2d68b910651d6216020689f1e016be87a2d0019ee3baeab  tokenizer.json
+4942d005604266809309cabc9f4e9cb89ce855d59b14681fdc0e1cc62ea26c4c  tokenizer_config.json
+efa87abb745fd48d9ee657d62d1a18899e4ee8eba75e47507dbb5991f3b7095a  embed_tokens.f16.bin
+aba6d66c11c29d0da579a44394b9621aca6466611be91053645be6a2d23bbdf4  r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc (tree)
+e30ca12f6ed6b5a0a25af97dfbbedc8c58dfd9db2f707ca130f7941bb12a57eb  r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc (tree)
+ed219b49d16d1bd7905452fdf653eba8778c26d0dd2766d7fc30876eac52cfe5  r2t2_lm_head_lut8.mlmodelc (tree)
+b34645f8671aec799b836fb4f32ff591d57d061c12ea2c24a3faf0a713b10695  R2T2AudioEncoder.mlmodelc (tree)

embed_tokens.f16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efa87abb745fd48d9ee657d62d1a18899e4ee8eba75e47507dbb5991f3b7095a
+size 622329856

r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cd2e5d8a5bf6e7698165f027d5de6e700c411014d53a8d1db8df6c2fc95e83b
+size 243

r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b1048f219d90e56c24832df9d307b0c1add26ae76864e5b8cf4075c15ba9a4c
+size 986

r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc/metadata.json

@@ -0,0 +1,321 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.anemll.chunk_no" : "1",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.anemll.context_length" : "1024",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.anemll.num_chunks" : "2",
+      "com.anemll.batch_size" : "128",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "com.anemll.lut_bits" : "8"
+    },
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 2048]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "position_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 1024]",
+        "name" : "causal_mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "current_pos",
+        "type" : "MultiArray"
+      }
+    ],
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 2048]",
+        "name" : "output_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1, 1024]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 1024, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 2048]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 56,
+          "Ios18.mul" : 224,
+          "Ios18.softmax" : 14,
+          "Ios18.matmul" : 28,
+          "Identity" : 1,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 29,
+          "Tile" : 28,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 73,
+          "Ios18.layerNorm" : 56,
+          "Ios18.sliceUpdate" : 28,
+          "Ios18.writeState" : 28,
+          "Ios18.reshape" : 86,
+          "Ios18.constexprLutToDense" : 98,
+          "Ios18.conv" : 98,
+          "Ios18.concat" : 140,
+          "Ios18.transpose" : 84,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 14,
+          "Ios18.sliceByIndex" : 140,
+          "Ios18.squeeze" : 42
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 128 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 128, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 128)",
+            "shortDescription" : "",
+            "shape" : "[128]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 128 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 128, 1024]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 1024, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 128 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 128, 2048]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "prefill",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 56,
+          "Ios18.mul" : 224,
+          "Ios18.softmax" : 14,
+          "Ios18.matmul" : 28,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 29,
+          "Tile" : 28,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 73,
+          "Ios18.layerNorm" : 56,
+          "Ios18.sliceUpdate" : 28,
+          "Ios18.writeState" : 28,
+          "Ios18.reshape" : 114,
+          "Ios18.constexprLutToDense" : 98,
+          "Ios18.conv" : 98,
+          "Ios18.concat" : 140,
+          "Ios18.transpose" : 128,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 14,
+          "Ios18.sliceByIndex" : 140,
+          "Ios18.squeeze" : 42
+        }
+      }
+    ],
+    "version" : "0.1.1",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+        "shortDescription" : "",
+        "shape" : "[56, 8, 1024, 128]",
+        "name" : "model_model_kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 56,
+      "Ios18.mul" : 224,
+      "Ios18.softmax" : 14,
+      "Ios18.matmul" : 28,
+      "Identity" : 1,
+      "Ios18.greaterEqual" : 2,
+      "Select" : 2,
+      "Ios18.readState" : 29,
+      "Tile" : 28,
+      "Ios18.gather" : 2,
+      "Ios18.add" : 73,
+      "Ios18.layerNorm" : 56,
+      "Ios18.sliceUpdate" : 28,
+      "Ios18.writeState" : 28,
+      "Ios18.reshape" : 86,
+      "Ios18.constexprLutToDense" : 98,
+      "Ios18.conv" : 98,
+      "Ios18.concat" : 140,
+      "Ios18.transpose" : 84,
+      "Ios18.cast" : 5,
+      "Ios18.silu" : 14,
+      "Ios18.sliceByIndex" : 140,
+      "Ios18.squeeze" : 42
+    },
+    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
+    "generatedClassName" : "r2t2_FFN_PF_lut8_chunk_01of02",
+    "author" : "Converted with Anemll v0.1.1",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

r2t2_FFN_PF_lut8_chunk_01of02.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74494c85747845fc4f27bfc1c77e6b81ec3ebd0a494aca59c35d59ab7df62485
+size 724179904

r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c90c7e7bf41e01fd443833700072119b021ea2c0816241bc6b303888181931d2
+size 243

r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e45f2ea058ea90c17e7ab6d48ab0451cfdc11a1167aa3971ddf32563f742a2d8
+size 986

r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc/metadata.json

@@ -0,0 +1,321 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.anemll.context_length" : "1024",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.anemll.lut_bits" : "8",
+      "com.anemll.num_chunks" : "2",
+      "com.anemll.batch_size" : "128",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "com.anemll.chunk_no" : "2"
+    },
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 2048]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "position_ids",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1024)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 1, 1024]",
+        "name" : "causal_mask",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Int32",
+        "formattedType" : "MultiArray (Int32 1)",
+        "shortDescription" : "",
+        "shape" : "[1]",
+        "name" : "current_pos",
+        "type" : "MultiArray"
+      }
+    ],
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 2048]",
+        "name" : "output_hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 1 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 1, 1024]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 1024, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 2048]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 56,
+          "Ios18.mul" : 226,
+          "Ios18.softmax" : 14,
+          "Ios18.matmul" : 28,
+          "Identity" : 1,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 29,
+          "Tile" : 28,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 73,
+          "Ios18.layerNorm" : 57,
+          "Ios18.sliceUpdate" : 28,
+          "Ios18.writeState" : 28,
+          "Ios18.reshape" : 86,
+          "Ios18.constexprLutToDense" : 98,
+          "Ios18.conv" : 98,
+          "Ios18.concat" : 141,
+          "Ios18.transpose" : 84,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 14,
+          "Ios18.sliceByIndex" : 141,
+          "Ios18.squeeze" : 42
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 128 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 128, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 128)",
+            "shortDescription" : "",
+            "shape" : "[128]",
+            "name" : "position_ids",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 128 × 1024)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 128, 1024]",
+            "name" : "causal_mask",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Int32",
+            "formattedType" : "MultiArray (Int32 1)",
+            "shortDescription" : "",
+            "shape" : "[1]",
+            "name" : "current_pos",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+        "storagePrecision" : "Mixed (Float16, Palettized (15 bits), Palettized (16 bits), Palettized (18 bits), UInt8)",
+        "stateSchema" : [
+          {
+            "dataType" : "Float16",
+            "isOptional" : "0",
+            "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+            "shortDescription" : "",
+            "shape" : "[56, 8, 1024, 128]",
+            "name" : "model_model_kv_cache_0",
+            "type" : "State"
+          }
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 128 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 128, 2048]",
+            "name" : "output_hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "prefill",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.expandDims" : 56,
+          "Ios18.mul" : 226,
+          "Ios18.softmax" : 14,
+          "Ios18.matmul" : 28,
+          "Ios18.greaterEqual" : 2,
+          "Select" : 2,
+          "Ios18.readState" : 29,
+          "Tile" : 28,
+          "Ios18.gather" : 2,
+          "Ios18.add" : 73,
+          "Ios18.layerNorm" : 57,
+          "Ios18.sliceUpdate" : 28,
+          "Ios18.writeState" : 28,
+          "Ios18.reshape" : 114,
+          "Ios18.constexprLutToDense" : 98,
+          "Ios18.conv" : 98,
+          "Ios18.concat" : 141,
+          "Ios18.transpose" : 128,
+          "Ios18.cast" : 5,
+          "Ios18.silu" : 14,
+          "Ios18.sliceByIndex" : 141,
+          "Ios18.squeeze" : 42
+        }
+      }
+    ],
+    "version" : "0.1.1",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+      {
+        "dataType" : "Float16",
+        "isOptional" : "0",
+        "formattedType" : "State (Float16 56 × 8 × 1024 × 128)",
+        "shortDescription" : "",
+        "shape" : "[56, 8, 1024, 128]",
+        "name" : "model_model_kv_cache_0",
+        "type" : "State"
+      }
+    ],
+    "computePrecision" : "Mixed (Float16, Int16, Int32, UInt16)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.expandDims" : 56,
+      "Ios18.mul" : 226,
+      "Ios18.softmax" : 14,
+      "Ios18.matmul" : 28,
+      "Identity" : 1,
+      "Ios18.greaterEqual" : 2,
+      "Select" : 2,
+      "Ios18.readState" : 29,
+      "Tile" : 28,
+      "Ios18.gather" : 2,
+      "Ios18.add" : 73,
+      "Ios18.layerNorm" : 57,
+      "Ios18.sliceUpdate" : 28,
+      "Ios18.writeState" : 28,
+      "Ios18.reshape" : 86,
+      "Ios18.constexprLutToDense" : 98,
+      "Ios18.conv" : 98,
+      "Ios18.concat" : 141,
+      "Ios18.transpose" : 84,
+      "Ios18.cast" : 5,
+      "Ios18.silu" : 14,
+      "Ios18.sliceByIndex" : 141,
+      "Ios18.squeeze" : 42
+    },
+    "shortDescription" : "Anemll Model: Multifunction FFN+Prefill",
+    "generatedClassName" : "r2t2_FFN_PF_lut8_chunk_02of02",
+    "author" : "Converted with Anemll v0.1.1",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

r2t2_FFN_PF_lut8_chunk_02of02.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2132cc8f5338b94f1b568c3df1d821d8b99db829cab291c56d56f6baaa0b20b
+size 724184064

r2t2_lm_head_lut8.mlmodelc/analytics/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c98575b5a199847eb87ba56275e4b3f58bf6d3b28d9275b6b51334e27a7efbb
+size 243

r2t2_lm_head_lut8.mlmodelc/coremldata.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552fdb564ca00497c313551966843e18eb04616c0a24190e64e0db1c5358a8da
+size 1264

r2t2_lm_head_lut8.mlmodelc/metadata.json

@@ -0,0 +1,481 @@
+[
+  {
+    "metadataOutputVersion" : "3.0",
+    "userDefinedMetadata" : {
+      "com.github.apple.coremltools.version" : "9.0",
+      "com.github.apple.coremltools.source" : "torch==2.8.0",
+      "com.anemll.context_length" : "1024",
+      "com.github.apple.coremltools.source_dialect" : "TorchScript",
+      "com.anemll.lm_head_chunk_sizes" : "9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496,9496",
+      "com.anemll.vocab_size" : "151936",
+      "com.anemll.batch_size" : "128",
+      "com.anemll.info" : "Converted with Anemll v0.1.1",
+      "com.anemll.argmax_in_model" : "true",
+      "com.anemll.lut_bits" : "8"
+    },
+    "availability" : {
+      "macOS" : "15.0",
+      "tvOS" : "18.0",
+      "visionOS" : "2.0",
+      "watchOS" : "11.0",
+      "iOS" : "18.0",
+      "macCatalyst" : "18.0"
+    },
+    "inputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 2048]",
+        "name" : "hidden_states",
+        "type" : "MultiArray"
+      }
+    ],
+    "outputSchema" : [
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits1",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits2",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits3",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits4",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits5",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits6",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits7",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits8",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits9",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits10",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits11",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits12",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits13",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits14",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits15",
+        "type" : "MultiArray"
+      },
+      {
+        "hasShapeFlexibility" : "0",
+        "isOptional" : "0",
+        "dataType" : "Float16",
+        "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+        "shortDescription" : "",
+        "shape" : "[1, 1, 9496]",
+        "name" : "logits16",
+        "type" : "MultiArray"
+      }
+    ],
+    "modelParameters" : [
+
+    ],
+    "storagePrecision" : "Mixed (Float16, Palettized (19 bits), UInt8)",
+    "method" : "predict",
+    "functions" : [
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int32)",
+        "storagePrecision" : "Mixed (Float16, Palettized (19 bits), UInt8)",
+        "stateSchema" : [
+
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits1",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits2",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits3",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits4",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits5",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits6",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits7",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits8",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits9",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits10",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits11",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits12",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits13",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits14",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits15",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 1 × 9496)",
+            "shortDescription" : "",
+            "shape" : "[1, 1, 9496]",
+            "name" : "logits16",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "infer",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.transpose" : 17,
+          "Ios18.constexprLutToDense" : 16,
+          "Ios18.expandDims" : 1,
+          "Ios18.conv" : 16,
+          "Ios18.squeeze" : 16
+        }
+      },
+      {
+        "inputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 1 × 128 × 2048)",
+            "shortDescription" : "",
+            "shape" : "[1, 128, 2048]",
+            "name" : "hidden_states",
+            "type" : "MultiArray"
+          }
+        ],
+        "computePrecision" : "Mixed (Float16, Int32)",
+        "storagePrecision" : "Mixed (Float16, Palettized (19 bits), UInt8)",
+        "stateSchema" : [
+
+        ],
+        "outputSchema" : [
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 128 × 16)",
+            "shortDescription" : "",
+            "shape" : "[128, 16]",
+            "name" : "argmax_val",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 128 × 16)",
+            "shortDescription" : "",
+            "shape" : "[128, 16]",
+            "name" : "argmax_hi",
+            "type" : "MultiArray"
+          },
+          {
+            "hasShapeFlexibility" : "0",
+            "isOptional" : "0",
+            "dataType" : "Float16",
+            "formattedType" : "MultiArray (Float16 128 × 16)",
+            "shortDescription" : "",
+            "shape" : "[128, 16]",
+            "name" : "argmax_lo",
+            "type" : "MultiArray"
+          }
+        ],
+        "name" : "verify",
+        "mlProgramOperationTypeHistogram" : {
+          "Ios18.squeeze" : 19,
+          "Ios18.mul" : 96,
+          "Ios18.sub" : 96,
+          "Ios18.concat" : 3,
+          "Ios18.clip" : 64,
+          "Ios18.transpose" : 4,
+          "Ios18.abs" : 16,
+          "Ios18.constexprLutToDense" : 16,
+          "Ios18.expandDims" : 1,
+          "Ios16.reduceMax" : 48,
+          "Ios18.conv" : 16
+        }
+      }
+    ],
+    "version" : "0.1.1",
+    "isUpdatable" : "0",
+    "defaultFunctionName" : "infer",
+    "specificationVersion" : 9,
+    "stateSchema" : [
+
+    ],
+    "computePrecision" : "Mixed (Float16, Int32)",
+    "mlProgramOperationTypeHistogram" : {
+      "Ios18.transpose" : 17,
+      "Ios18.constexprLutToDense" : 16,
+      "Ios18.expandDims" : 1,
+      "Ios18.conv" : 16,
+      "Ios18.squeeze" : 16
+    },
+    "shortDescription" : "Anemll Model: Multifunction LM Head",
+    "generatedClassName" : "r2t2_lm_head_PV_lut8",
+    "author" : "Converted with Anemll v0.1.1",
+    "modelType" : {
+      "name" : "MLModelType_mlProgram"
+    }
+  }
+]

r2t2_lm_head_lut8.mlmodelc/weights/weight.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dbed03e7ae581e50c84ec9ad6fbf112bfbbfcbefe7247a3753e1cb31565ebc0
+size 320948144

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0499602714160467f2d68b910651d6216020689f1e016be87a2d0019ee3baeab
+size 11429499

tokenizer_config.json

@@ -0,0 +1,549 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<|audio_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|audio_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151671": {
+      "content": "<tts_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151672": {
+      "content": "<tts_text_bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151673": {
+      "content": "<tts_text_eod>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151674": {
+      "content": "<tts_text_bos_single>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151675": {
+      "content": "<non_speech>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151676": {
+      "content": "<|audio_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151677": {
+      "content": "<blank1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151678": {
+      "content": "<blank2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151679": {
+      "content": "<blank3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151680": {
+      "content": "<blank4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151681": {
+      "content": "<blank5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151682": {
+      "content": "<blank6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151683": {
+      "content": "<blank7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151684": {
+      "content": "<blank8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151685": {
+      "content": "<blank9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151686": {
+      "content": "<blank10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151687": {
+      "content": "<blank11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151688": {
+      "content": "<blank12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151689": {
+      "content": "<blank13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151690": {
+      "content": "<blank14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151691": {
+      "content": "<blank15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151692": {
+      "content": "<blank16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151693": {
+      "content": "<blank17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151694": {
+      "content": "<blank18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151695": {
+      "content": "<blank19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151696": {
+      "content": "<blank20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151697": {
+      "content": "<blank21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151698": {
+      "content": "<blank22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151699": {
+      "content": "<blank23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151700": {
+      "content": "<blank24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151701": {
+      "content": "<blank25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151702": {
+      "content": "<blank26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151703": {
+      "content": "<blank27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151704": {
+      "content": "<asr_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<|audio_start|>",
+    "<|audio_end|>",
+    "<tts_pad>",
+    "<tts_text_bos>",
+    "<tts_text_bos_single>",
+    "<|audio_pad|>"
+  ],
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "image_token": "<|image_pad|>",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3ASRProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}