Upload folder using huggingface_hub

.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
+HRM-Text-1B-BF16.gguf filter=lfs diff=lfs merge=lfs -text

HRM-Text-1B-BF16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dd5e2ef55e40c46db0d0cb4cf1427a4e72da34fee36f0d2b73d081d0e1c2010
+size 2367995648

LICENSE

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

README.md

@@ -0,0 +1,136 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: gguf
+pipeline_tag: text-generation
+base_model: sapientinc/HRM-Text-1B
+base_model_relation: quantized
+tags:
+- gguf
+- bf16
+- quantized
+- llama.cpp
+- hrm
+- hierarchical-reasoning
+- prefix-lm
+- pre-alignment
+- non-chat
+- non-instruction-tuned
+---
+
+# HRM-Text-1B GGUF
+
+This repository contains a BF16 GGUF conversion of [`sapientinc/HRM-Text-1B`](https://huggingface.co/sapientinc/HRM-Text-1B).
+
+The GGUF uses:
+
+- `general.architecture = hrm_text`
+- BF16 tensor storage
+- the original tokenizer from `tokenizer.json`
+- no injected chat template
+
+This is not a chat model and is not instruction tuned. "Useful output" for this repository means alignment with the original Transformers model on the same prompt, not chat-assistant behavior.
+
+## Compatibility Notice
+
+Standard upstream `llama.cpp`, Ollama, LM Studio, and `llama-cpp-python` are expected not to load this file until `hrm_text` is supported upstream.
+
+Use the included patch:
+
+```text
+runtime/llama.cpp-hrm_text.patch
+```
+
+The patch was built against:
+
+```text
+ggml-org/llama.cpp commit 6a257d44633d4a752183ed778b88d2924d0a6b9d
+```
+
+Only the normal causal generation path is implemented in the patched runtime. Prefix-LM bidirectional `token_type_ids` are not supported by the `llama.cpp` path in this release.
+
+## Files
+
+| File | Description |
+| --- | --- |
+| `HRM-Text-1B-BF16.gguf` | BF16 GGUF conversion of `sapientinc/HRM-Text-1B` |
+| `runtime/llama.cpp-hrm_text.patch` | Patch adding `hrm_text` conversion and runtime support to the clean `llama.cpp` base commit |
+| `reports/validation/final_report.md` | Human-readable conversion and validation report |
+| `reports/validation/baseline_transformers.json` | Transformers baseline prompts, logits, and continuations |
+| `reports/validation/bf16_tensor_validation.json` | Tensor-level GGUF validation |
+| `reports/validation/bf16_vs_hf.json` | Runtime logit and text validation |
+
+## Provenance
+
+| Item | Value |
+| --- | --- |
+| Source model | `sapientinc/HRM-Text-1B` |
+| Source snapshot SHA | `2285b999f6fb8a5b16e0cc313a9e8e4fe447140d` |
+| Source `model.safetensors` SHA256 | `F8FE2B2BF6948414E8E8D6538659198726D98F967C55B533B7AABE8A1FA9A584` |
+| GGUF SHA256 | `2DD5E2EF55E40C46DB0D0CB4CF1427A4E72DA34FEE36F0D2B73D081D0E1C2010` |
+| GGUF size | `2,367,995,648` bytes |
+| llama.cpp base commit | `6a257d44633d4a752183ed778b88d2924d0a6b9d` |
+
+## Validation Summary
+
+Validation was performed from a clean source snapshot and a clean `llama.cpp` base checkout.
+
+| Check | Result |
+| --- | --- |
+| Tensor validation | Pass, `259/259` tensors found and compared |
+| Tensor values | BF16 tensor bits match HF after expected BF16 conversion |
+| Prompt token IDs | Match for all validation prompts |
+| Next-token top-1 | Match on `4/4` prompts |
+| Top-10 overlap | `10/10` for all prompts |
+| Text validation | BF16 GGUF continuations are aligned with Transformers baseline |
+
+Full-vocab mean absolute logit error:
+
+| Prompt | MAE |
+| --- | ---: |
+| `The quick brown fox` | `0.0199148655` |
+| `In a distant future, humanity` | `0.0051696529` |
+| `Question: What is 2+2?\nAnswer:` | `0.0076530445` |
+| `def fibonacci(n):` | `0.0045031775` |
+
+The original model already repeats on some prompts. Repetition by itself is not treated as a conversion failure unless it is newly introduced by the GGUF runtime. The BF16 GGUF validation did not reproduce the unrelated garbage pattern seen in a previous broken conversion attempt.
+
+## Example Runtime Setup
+
+Download this repository:
+
+```powershell
+pip install -U huggingface_hub
+hf download sinimiini/HRM-Text-1B-GGUF --local-dir HRM-Text-1B-GGUF
+```
+
+Patch and build `llama.cpp`:
+
+```powershell
+git clone https://github.com/ggml-org/llama.cpp
+cd llama.cpp
+git checkout 6a257d44633d4a752183ed778b88d2924d0a6b9d
+git apply ..\HRM-Text-1B-GGUF\runtime\llama.cpp-hrm_text.patch
+cmake -B build -S . -DGGML_NATIVE=OFF
+cmake --build build --config Release --target llama-cli llama-completion llama-results
+```
+
+Run a short causal-generation smoke test:
+
+```powershell
+.\build\bin\Release\llama-cli.exe -m ..\HRM-Text-1B-GGUF\HRM-Text-1B-BF16.gguf -p "The quick brown fox" -n 32 --temp 0 --no-conversation
+```
+
+Depending on the generator binary and `llama.cpp` build type, the executable may be under `build\bin\llama-cli.exe` instead of `build\bin\Release\llama-cli.exe`.
+
+## Limitations
+
+- `hrm_text` is a custom GGUF architecture in this conversion.
+- Generic GGUF runners will not work until they implement the HRM runtime graph.
+- Prefix-LM bidirectional attention with `token_type_ids` is not implemented in the patched `llama.cpp` path.
+- Q8_0 and other quantized variants are intentionally not included in this repository.
+
+## License
+
+The source model is released under the Apache 2.0 license. See [`LICENSE`](./LICENSE).

reports/validation/baseline_transformers.json

@@ -0,0 +1,521 @@
+{
+  "model_dir": "D:\\Projects\\Active\\HRM-Text\\hrm-text-gguf\\fresh\\models\\hf\\HRM-Text-1B",
+  "created_at_unix": 1779317536.288255,
+  "elapsed_seconds": 110.19880509376526,
+  "torch_dtype": "float32",
+  "prompts": [
+    {
+      "prompt": "The quick brown fox",
+      "input_ids": [
+        341,
+        3568,
+        9054,
+        20102
+      ],
+      "next_top20": [
+        {
+          "token_id": 20102,
+          "logit": 14.282323837280273
+        },
+        {
+          "token_id": 40036,
+          "logit": 7.984903335571289
+        },
+        {
+          "token_id": 11979,
+          "logit": 6.678519248962402
+        },
+        {
+          "token_id": 3568,
+          "logit": 6.593014717102051
+        },
+        {
+          "token_id": 4349,
+          "logit": 6.3277907371521
+        },
+        {
+          "token_id": 42,
+          "logit": 6.296438694000244
+        },
+        {
+          "token_id": 3152,
+          "logit": 5.423942565917969
+        },
+        {
+          "token_id": 2301,
+          "logit": 5.353857517242432
+        },
+        {
+          "token_id": 44,
+          "logit": 5.17809534072876
+        },
+        {
+          "token_id": 3558,
+          "logit": 4.873218059539795
+        },
+        {
+          "token_id": 3412,
+          "logit": 4.821749210357666
+        },
+        {
+          "token_id": 5002,
+          "logit": 4.811767578125
+        },
+        {
+          "token_id": 761,
+          "logit": 4.7139716148376465
+        },
+        {
+          "token_id": 19444,
+          "logit": 4.702877521514893
+        },
+        {
+          "token_id": 446,
+          "logit": 4.699982166290283
+        },
+        {
+          "token_id": 16001,
+          "logit": 4.579901218414307
+        },
+        {
+          "token_id": 322,
+          "logit": 4.416025638580322
+        },
+        {
+          "token_id": 3297,
+          "logit": 4.394478797912598
+        },
+        {
+          "token_id": 8636,
+          "logit": 4.318077564239502
+        },
+        {
+          "token_id": 12672,
+          "logit": 4.272546768188477
+        }
+      ],
+      "generated_ids": [
+        341,
+        3568,
+        9054,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102,
+        20102
+      ],
+      "generated_text": "The quick brown fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox"
+    },
+    {
+      "prompt": "In a distant future, humanity",
+      "input_ids": [
+        931,
+        236,
+        95,
+        9494,
+        2025,
+        42,
+        13279
+      ],
+      "next_top20": [
+        {
+          "token_id": 385,
+          "logit": 8.0965576171875
+        },
+        {
+          "token_id": 42,
+          "logit": 7.368254661560059
+        },
+        {
+          "token_id": 322,
+          "logit": 7.224921226501465
+        },
+        {
+          "token_id": 5106,
+          "logit": 6.963152885437012
+        },
+        {
+          "token_id": 5835,
+          "logit": 6.56166934967041
+        },
+        {
+          "token_id": 769,
+          "logit": 6.253977298736572
+        },
+        {
+          "token_id": 599,
+          "logit": 6.24298620223999
+        },
+        {
+          "token_id": 1980,
+          "logit": 6.066655158996582
+        },
+        {
+          "token_id": 295,
+          "logit": 6.027203559875488
+        },
+        {
+          "token_id": 2156,
+          "logit": 5.429737091064453
+        },
+        {
+          "token_id": 379,
+          "logit": 5.259855270385742
+        },
+        {
+          "token_id": 5226,
+          "logit": 5.044851303100586
+        },
+        {
+          "token_id": 10755,
+          "logit": 4.90900993347168
+        },
+        {
+          "token_id": 446,
+          "logit": 4.904206275939941
+        },
+        {
+          "token_id": 236,
+          "logit": 4.781126976013184
+        },
+        {
+          "token_id": 2026,
+          "logit": 4.646615982055664
+        },
+        {
+          "token_id": 307,
+          "logit": 4.629412651062012
+        },
+        {
+          "token_id": 1287,
+          "logit": 4.488158702850342
+        },
+        {
+          "token_id": 3891,
+          "logit": 4.160832405090332
+        },
+        {
+          "token_id": 5671,
+          "logit": 4.064340114593506
+        }
+      ],
+      "generated_ids": [
+        931,
+        236,
+        95,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494,
+        2025,
+        42,
+        13279,
+        385,
+        9494
+      ],
+      "generated_text": "In a distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant"
+    },
+    {
+      "prompt": "Question: What is 2+2?\nAnswer:",
+      "input_ids": [
+        1069,
+        56,
+        866,
+        322,
+        236,
+        48,
+        41,
+        48,
+        1047,
+        1180,
+        56
+      ],
+      "next_top20": [
+        {
+          "token_id": 236,
+          "logit": 9.961008071899414
+        },
+        {
+          "token_id": 391,
+          "logit": 6.013479709625244
+        },
+        {
+          "token_id": 315,
+          "logit": 5.94870138168335
+        },
+        {
+          "token_id": 866,
+          "logit": 5.673839569091797
+        },
+        {
+          "token_id": 395,
+          "logit": 5.604125499725342
+        },
+        {
+          "token_id": 5444,
+          "logit": 5.225252151489258
+        },
+        {
+          "token_id": 4746,
+          "logit": 4.788036346435547
+        },
+        {
+          "token_id": 1827,
+          "logit": 4.560125827789307
+        },
+        {
+          "token_id": 369,
+          "logit": 3.9722537994384766
+        },
+        {
+          "token_id": 970,
+          "logit": 3.7374000549316406
+        },
+        {
+          "token_id": 725,
+          "logit": 3.7227249145507812
+        },
+        {
+          "token_id": 421,
+          "logit": 3.6337995529174805
+        },
+        {
+          "token_id": 731,
+          "logit": 3.230243444442749
+        },
+        {
+          "token_id": 401,
+          "logit": 3.176685094833374
+        },
+        {
+          "token_id": 2286,
+          "logit": 3.169259786605835
+        },
+        {
+          "token_id": 1422,
+          "logit": 3.161581516265869
+        },
+        {
+          "token_id": 10528,
+          "logit": 3.150108575820923
+        },
+        {
+          "token_id": 1544,
+          "logit": 3.148630380630493
+        },
+        {
+          "token_id": 973,
+          "logit": 3.134061336517334
+        },
+        {
+          "token_id": 4286,
+          "logit": 3.118112325668335
+        }
+      ],
+      "generated_ids": [
+        1069,
+        56,
+        866,
+        322,
+        236,
+        48,
+        41,
+        48,
+        1047,
+        1180,
+        56,
+        236,
+        52,
+        11
+      ],
+      "generated_text": "Question: What is 2+2?\nAnswer: 6<|box_end|>"
+    },
+    {
+      "prompt": "def fibonacci(n):",
+      "input_ids": [
+        26763,
+        8430,
+        21728,
+        3145,
+        10018
+      ],
+      "next_top20": [
+        {
+          "token_id": 56,
+          "logit": 10.336507797241211
+        },
+        {
+          "token_id": 2904,
+          "logit": 7.036001205444336
+        },
+        {
+          "token_id": 11,
+          "logit": 6.869954586029053
+        },
+        {
+          "token_id": 10018,
+          "logit": 6.520134449005127
+        },
+        {
+          "token_id": 108,
+          "logit": 6.356081008911133
+        },
+        {
+          "token_id": 318,
+          "logit": 6.157332420349121
+        },
+        {
+          "token_id": 236,
+          "logit": 6.079721927642822
+        },
+        {
+          "token_id": 38,
+          "logit": 5.885505676269531
+        },
+        {
+          "token_id": 68,
+          "logit": 5.052194118499756
+        },
+        {
+          "token_id": 39,
+          "logit": 4.714491844177246
+        },
+        {
+          "token_id": 76,
+          "logit": 4.675869464874268
+        },
+        {
+          "token_id": 57,
+          "logit": 4.6666717529296875
+        },
+        {
+          "token_id": 59,
+          "logit": 4.655692100524902
+        },
+        {
+          "token_id": 1941,
+          "logit": 4.59184455871582
+        },
+        {
+          "token_id": 401,
+          "logit": 4.578482151031494
+        },
+        {
+          "token_id": 395,
+          "logit": 4.54650354385376
+        },
+        {
+          "token_id": 8430,
+          "logit": 4.537847518920898
+        },
+        {
+          "token_id": 95,
+          "logit": 4.34259033203125
+        },
+        {
+          "token_id": 364,
+          "logit": 4.28465461730957
+        },
+        {
+          "token_id": 3145,
+          "logit": 4.255484580993652
+        }
+      ],
+      "generated_ids": [
+        26763,
+        8430,
+        21728,
+        3145,
+        10018,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56,
+        56
+      ],
+      "generated_text": "def fibonacci(n):::::::::::::::::::::::::::::::::"
+    }
+  ]
+}

reports/validation/bf16_tensor_validation.json

@@ -0,0 +1,18 @@
+{
+  "gguf": "fresh\\out\\gguf\\HRM-Text-1B-BF16.gguf",
+  "hf_dir": "fresh\\models\\hf\\HRM-Text-1B",
+  "metadata": {
+    "general.architecture": "hrm_text",
+    "hrm_text.block_count": 128,
+    "hrm_text.layers_per_stack": 16,
+    "hrm_text.h_cycles": 2,
+    "hrm_text.l_cycles": 3,
+    "hrm_text.prefix_lm": true,
+    "hrm_text.embedding_scale": 39.191837310791016
+  },
+  "expected_tensor_count": 259,
+  "actual_tensor_count": 259,
+  "compared_tensor_count": 259,
+  "passed": true,
+  "failures": []
+}

reports/validation/bf16_vs_hf.json

@@ -0,0 +1,782 @@
+{
+  "hf_dir": "fresh\\models\\hf\\HRM-Text-1B",
+  "gguf": "fresh\\out\\gguf\\HRM-Text-1B-BF16.gguf",
+  "created_at_unix": 1779321040.6954496,
+  "elapsed_seconds": 128.6622235774994,
+  "hf_dtype": "float32",
+  "checks": {
+    "prompt_tokens_match": true,
+    "same_next_top1_all_prompts": true,
+    "top10_overlap_at_least_8_all_prompts": true,
+    "full_vocab_mean_abs_logit_error_lte_0_03_all_prompts": true,
+    "passed": true
+  },
+  "prompts": [
+    {
+      "prompt": "The quick brown fox",
+      "hf_input_ids": [
+        341,
+        3568,
+        9054,
+        20102
+      ],
+      "gguf_input_ids": [
+        341,
+        3568,
+        9054,
+        20102
+      ],
+      "tokens_match": true,
+      "hf_next_top20": [
+        {
+          "token_id": 20102,
+          "logit": 14.282323837280273
+        },
+        {
+          "token_id": 40036,
+          "logit": 7.984903335571289
+        },
+        {
+          "token_id": 11979,
+          "logit": 6.678519248962402
+        },
+        {
+          "token_id": 3568,
+          "logit": 6.593014717102051
+        },
+        {
+          "token_id": 4349,
+          "logit": 6.3277907371521
+        },
+        {
+          "token_id": 42,
+          "logit": 6.296438694000244
+        },
+        {
+          "token_id": 3152,
+          "logit": 5.423942565917969
+        },
+        {
+          "token_id": 2301,
+          "logit": 5.353857517242432
+        },
+        {
+          "token_id": 44,
+          "logit": 5.17809534072876
+        },
+        {
+          "token_id": 3558,
+          "logit": 4.873218059539795
+        },
+        {
+          "token_id": 3412,
+          "logit": 4.821749210357666
+        },
+        {
+          "token_id": 5002,
+          "logit": 4.811767578125
+        },
+        {
+          "token_id": 761,
+          "logit": 4.7139716148376465
+        },
+        {
+          "token_id": 19444,
+          "logit": 4.702877521514893
+        },
+        {
+          "token_id": 446,
+          "logit": 4.699982166290283
+        },
+        {
+          "token_id": 16001,
+          "logit": 4.579901218414307
+        },
+        {
+          "token_id": 322,
+          "logit": 4.416025638580322
+        },
+        {
+          "token_id": 3297,
+          "logit": 4.394478797912598
+        },
+        {
+          "token_id": 8636,
+          "logit": 4.318077564239502
+        },
+        {
+          "token_id": 12672,
+          "logit": 4.272546768188477
+        }
+      ],
+      "gguf_next_top20": [
+        {
+          "token_id": 20102,
+          "logit": 14.297157287597656
+        },
+        {
+          "token_id": 40036,
+          "logit": 7.994879722595215
+        },
+        {
+          "token_id": 11979,
+          "logit": 6.699657440185547
+        },
+        {
+          "token_id": 3568,
+          "logit": 6.626206398010254
+        },
+        {
+          "token_id": 4349,
+          "logit": 6.35108757019043
+        },
+        {
+          "token_id": 42,
+          "logit": 6.271071434020996
+        },
+        {
+          "token_id": 3152,
+          "logit": 5.424627304077148
+        },
+        {
+          "token_id": 2301,
+          "logit": 5.3609843254089355
+        },
+        {
+          "token_id": 44,
+          "logit": 5.178180694580078
+        },
+        {
+          "token_id": 3558,
+          "logit": 4.875790596008301
+        },
+        {
+          "token_id": 5002,
+          "logit": 4.839702606201172
+        },
+        {
+          "token_id": 3412,
+          "logit": 4.824095249176025
+        },
+        {
+          "token_id": 761,
+          "logit": 4.718862056732178
+        },
+        {
+          "token_id": 19444,
+          "logit": 4.698058128356934
+        },
+        {
+          "token_id": 446,
+          "logit": 4.689098358154297
+        },
+        {
+          "token_id": 16001,
+          "logit": 4.590203762054443
+        },
+        {
+          "token_id": 3297,
+          "logit": 4.408023357391357
+        },
+        {
+          "token_id": 322,
+          "logit": 4.394444942474365
+        },
+        {
+          "token_id": 8636,
+          "logit": 4.318354606628418
+        },
+        {
+          "token_id": 12672,
+          "logit": 4.2834038734436035
+        }
+      ],
+      "top1_match": true,
+      "top10_overlap": 10,
+      "full_vocab_mean_abs_logit_error": 0.019914865493774414,
+      "top20_union_mean_abs_logit_error": 0.012285495176911354,
+      "hf_generated_suffix": " fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox",
+      "gguf_generated_suffix": " fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox fox\n\n"
+    },
+    {
+      "prompt": "In a distant future, humanity",
+      "hf_input_ids": [
+        931,
+        236,
+        95,
+        9494,
+        2025,
+        42,
+        13279
+      ],
+      "gguf_input_ids": [
+        931,
+        236,
+        95,
+        9494,
+        2025,
+        42,
+        13279
+      ],
+      "tokens_match": true,
+      "hf_next_top20": [
+        {
+          "token_id": 385,
+          "logit": 8.0965576171875
+        },
+        {
+          "token_id": 42,
+          "logit": 7.368254661560059
+        },
+        {
+          "token_id": 322,
+          "logit": 7.224921226501465
+        },
+        {
+          "token_id": 5106,
+          "logit": 6.963152885437012
+        },
+        {
+          "token_id": 5835,
+          "logit": 6.56166934967041
+        },
+        {
+          "token_id": 769,
+          "logit": 6.253977298736572
+        },
+        {
+          "token_id": 599,
+          "logit": 6.24298620223999
+        },
+        {
+          "token_id": 1980,
+          "logit": 6.066655158996582
+        },
+        {
+          "token_id": 295,
+          "logit": 6.027203559875488
+        },
+        {
+          "token_id": 2156,
+          "logit": 5.429737091064453
+        },
+        {
+          "token_id": 379,
+          "logit": 5.259855270385742
+        },
+        {
+          "token_id": 5226,
+          "logit": 5.044851303100586
+        },
+        {
+          "token_id": 10755,
+          "logit": 4.90900993347168
+        },
+        {
+          "token_id": 446,
+          "logit": 4.904206275939941
+        },
+        {
+          "token_id": 236,
+          "logit": 4.781126976013184
+        },
+        {
+          "token_id": 2026,
+          "logit": 4.646615982055664
+        },
+        {
+          "token_id": 307,
+          "logit": 4.629412651062012
+        },
+        {
+          "token_id": 1287,
+          "logit": 4.488158702850342
+        },
+        {
+          "token_id": 3891,
+          "logit": 4.160832405090332
+        },
+        {
+          "token_id": 5671,
+          "logit": 4.064340114593506
+        }
+      ],
+      "gguf_next_top20": [
+        {
+          "token_id": 385,
+          "logit": 8.094616889953613
+        },
+        {
+          "token_id": 42,
+          "logit": 7.381193161010742
+        },
+        {
+          "token_id": 322,
+          "logit": 7.22892951965332
+        },
+        {
+          "token_id": 5106,
+          "logit": 6.968372344970703
+        },
+        {
+          "token_id": 5835,
+          "logit": 6.5758562088012695
+        },
+        {
+          "token_id": 769,
+          "logit": 6.294882297515869
+        },
+        {
+          "token_id": 599,
+          "logit": 6.259007453918457
+        },
+        {
+          "token_id": 1980,
+          "logit": 6.067761421203613
+        },
+        {
+          "token_id": 295,
+          "logit": 6.029950141906738
+        },
+        {
+          "token_id": 2156,
+          "logit": 5.428796768188477
+        },
+        {
+          "token_id": 379,
+          "logit": 5.263803005218506
+        },
+        {
+          "token_id": 5226,
+          "logit": 5.066612243652344
+        },
+        {
+          "token_id": 446,
+          "logit": 4.910100936889648
+        },
+        {
+          "token_id": 10755,
+          "logit": 4.904460430145264
+        },
+        {
+          "token_id": 236,
+          "logit": 4.739671230316162
+        },
+        {
+          "token_id": 2026,
+          "logit": 4.661045074462891
+        },
+        {
+          "token_id": 307,
+          "logit": 4.627893447875977
+        },
+        {
+          "token_id": 1287,
+          "logit": 4.507448196411133
+        },
+        {
+          "token_id": 3891,
+          "logit": 4.162245273590088
+        },
+        {
+          "token_id": 5671,
+          "logit": 4.059610366821289
+        }
+      ],
+      "top1_match": true,
+      "top10_overlap": 10,
+      "full_vocab_mean_abs_logit_error": 0.005169652868062258,
+      "top20_union_mean_abs_logit_error": 0.010950112715363503,
+      "hf_generated_suffix": "'s distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant",
+      "gguf_generated_suffix": "'s distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant future, humanity's distant\n\n"
+    },
+    {
+      "prompt": "Question: What is 2+2?\nAnswer:",
+      "hf_input_ids": [
+        1069,
+        56,
+        866,
+        322,
+        236,
+        48,
+        41,
+        48,
+        1047,
+        1180,
+        56
+      ],
+      "gguf_input_ids": [
+        1069,
+        56,
+        866,
+        322,
+        236,
+        48,
+        41,
+        48,
+        1047,
+        1180,
+        56
+      ],
+      "tokens_match": true,
+      "hf_next_top20": [
+        {
+          "token_id": 236,
+          "logit": 9.961008071899414
+        },
+        {
+          "token_id": 391,
+          "logit": 6.013479709625244
+        },
+        {
+          "token_id": 315,
+          "logit": 5.94870138168335
+        },
+        {
+          "token_id": 866,
+          "logit": 5.673839569091797
+        },
+        {
+          "token_id": 395,
+          "logit": 5.604125499725342
+        },
+        {
+          "token_id": 5444,
+          "logit": 5.225252151489258
+        },
+        {
+          "token_id": 4746,
+          "logit": 4.788036346435547
+        },
+        {
+          "token_id": 1827,
+          "logit": 4.560125827789307
+        },
+        {
+          "token_id": 369,
+          "logit": 3.9722537994384766
+        },
+        {
+          "token_id": 970,
+          "logit": 3.7374000549316406
+        },
+        {
+          "token_id": 725,
+          "logit": 3.7227249145507812
+        },
+        {
+          "token_id": 421,
+          "logit": 3.6337995529174805
+        },
+        {
+          "token_id": 731,
+          "logit": 3.230243444442749
+        },
+        {
+          "token_id": 401,
+          "logit": 3.176685094833374
+        },
+        {
+          "token_id": 2286,
+          "logit": 3.169259786605835
+        },
+        {
+          "token_id": 1422,
+          "logit": 3.161581516265869
+        },
+        {
+          "token_id": 10528,
+          "logit": 3.150108575820923
+        },
+        {
+          "token_id": 1544,
+          "logit": 3.148630380630493
+        },
+        {
+          "token_id": 973,
+          "logit": 3.134061336517334
+        },
+        {
+          "token_id": 4286,
+          "logit": 3.118112325668335
+        }
+      ],
+      "gguf_next_top20": [
+        {
+          "token_id": 236,
+          "logit": 9.97547435760498
+        },
+        {
+          "token_id": 391,
+          "logit": 6.012524604797363
+        },
+        {
+          "token_id": 315,
+          "logit": 5.968222618103027
+        },
+        {
+          "token_id": 866,
+          "logit": 5.672043323516846
+        },
+        {
+          "token_id": 395,
+          "logit": 5.606063365936279
+        },
+        {
+          "token_id": 5444,
+          "logit": 5.2098188400268555
+        },
+        {
+          "token_id": 4746,
+          "logit": 4.777042388916016
+        },
+        {
+          "token_id": 1827,
+          "logit": 4.54682731628418
+        },
+        {
+          "token_id": 369,
+          "logit": 3.9637503623962402
+        },
+        {
+          "token_id": 970,
+          "logit": 3.765744686126709
+        },
+        {
+          "token_id": 725,
+          "logit": 3.7245254516601562
+        },
+        {
+          "token_id": 421,
+          "logit": 3.630314350128174
+        },
+        {
+          "token_id": 731,
+          "logit": 3.2161593437194824
+        },
+        {
+          "token_id": 401,
+          "logit": 3.1881794929504395
+        },
+        {
+          "token_id": 2286,
+          "logit": 3.168586254119873
+        },
+        {
+          "token_id": 1422,
+          "logit": 3.151968240737915
+        },
+        {
+          "token_id": 10528,
+          "logit": 3.148939847946167
+        },
+        {
+          "token_id": 1544,
+          "logit": 3.1278254985809326
+        },
+        {
+          "token_id": 973,
+          "logit": 3.1256284713745117
+        },
+        {
+          "token_id": 4286,
+          "logit": 3.0892391204833984
+        }
+      ],
+      "top1_match": true,
+      "top10_overlap": 10,
+      "full_vocab_mean_abs_logit_error": 0.0076530445367097855,
+      "top20_union_mean_abs_logit_error": 0.01078406535089016,
+      "hf_generated_suffix": " 6<|box_end|>",
+      "gguf_generated_suffix": " 6 [end of text]\n\n\n"
+    },
+    {
+      "prompt": "def fibonacci(n):",
+      "hf_input_ids": [
+        26763,
+        8430,
+        21728,
+        3145,
+        10018
+      ],
+      "gguf_input_ids": [
+        26763,
+        8430,
+        21728,
+        3145,
+        10018
+      ],
+      "tokens_match": true,
+      "hf_next_top20": [
+        {
+          "token_id": 56,
+          "logit": 10.336507797241211
+        },
+        {
+          "token_id": 2904,
+          "logit": 7.036001205444336
+        },
+        {
+          "token_id": 11,
+          "logit": 6.869954586029053
+        },
+        {
+          "token_id": 10018,
+          "logit": 6.520134449005127
+        },
+        {
+          "token_id": 108,
+          "logit": 6.356081008911133
+        },
+        {
+          "token_id": 318,
+          "logit": 6.157332420349121
+        },
+        {
+          "token_id": 236,
+          "logit": 6.079721927642822
+        },
+        {
+          "token_id": 38,
+          "logit": 5.885505676269531
+        },
+        {
+          "token_id": 68,
+          "logit": 5.052194118499756
+        },
+        {
+          "token_id": 39,
+          "logit": 4.714491844177246
+        },
+        {
+          "token_id": 76,
+          "logit": 4.675869464874268
+        },
+        {
+          "token_id": 57,
+          "logit": 4.6666717529296875
+        },
+        {
+          "token_id": 59,
+          "logit": 4.655692100524902
+        },
+        {
+          "token_id": 1941,
+          "logit": 4.59184455871582
+        },
+        {
+          "token_id": 401,
+          "logit": 4.578482151031494
+        },
+        {
+          "token_id": 395,
+          "logit": 4.54650354385376
+        },
+        {
+          "token_id": 8430,
+          "logit": 4.537847518920898
+        },
+        {
+          "token_id": 95,
+          "logit": 4.34259033203125
+        },
+        {
+          "token_id": 364,
+          "logit": 4.28465461730957
+        },
+        {
+          "token_id": 3145,
+          "logit": 4.255484580993652
+        }
+      ],
+      "gguf_next_top20": [
+        {
+          "token_id": 56,
+          "logit": 10.327644348144531
+        },
+        {
+          "token_id": 2904,
+          "logit": 7.035848140716553
+        },
+        {
+          "token_id": 11,
+          "logit": 6.860950946807861
+        },
+        {
+          "token_id": 10018,
+          "logit": 6.495933532714844
+        },
+        {
+          "token_id": 108,
+          "logit": 6.341927528381348
+        },
+        {
+          "token_id": 318,
+          "logit": 6.146999359130859
+        },
+        {
+          "token_id": 236,
+          "logit": 6.0702805519104
+        },
+        {
+          "token_id": 38,
+          "logit": 5.865842819213867
+        },
+        {
+          "token_id": 68,
+          "logit": 5.02256965637207
+        },
+        {
+          "token_id": 39,
+          "logit": 4.66829252243042
+        },
+        {
+          "token_id": 76,
+          "logit": 4.6676859855651855
+        },
+        {
+          "token_id": 59,
+          "logit": 4.662688255310059
+        },
+        {
+          "token_id": 57,
+          "logit": 4.66217041015625
+        },
+        {
+          "token_id": 1941,
+          "logit": 4.598584175109863
+        },
+        {
+          "token_id": 401,
+          "logit": 4.574923515319824
+        },
+        {
+          "token_id": 395,
+          "logit": 4.532867431640625
+        },
+        {
+          "token_id": 8430,
+          "logit": 4.5034050941467285
+        },
+        {
+          "token_id": 95,
+          "logit": 4.318176746368408
+        },
+        {
+          "token_id": 364,
+          "logit": 4.2872209548950195
+        },
+        {
+          "token_id": 48,
+          "logit": 4.243288516998291
+        }
+      ],
+      "top1_match": true,
+      "top10_overlap": 10,
+      "full_vocab_mean_abs_logit_error": 0.0045031774789094925,
+      "top20_union_mean_abs_logit_error": 0.01457904651761055,
+      "hf_generated_suffix": "::::::::::::::::::::::::::::::::",
+      "gguf_generated_suffix": "::::::::::::::::::::::::::::::::\n\n"
+    }
+  ]
+}

reports/validation/final_report.md

@@ -0,0 +1,48 @@
+# HRM-Text-1B BF16 GGUF Validation Report
+
+Date: 2026-05-21
+
+## Sources
+
+- HF model: `sapientinc/HRM-Text-1B`
+- HF snapshot SHA: `2285b999f6fb8a5b16e0cc313a9e8e4fe447140d`
+- HF `model.safetensors` SHA256: `F8FE2B2BF6948414E8E8D6538659198726D98F967C55B533B7AABE8A1FA9A584`
+- llama.cpp base commit: `6a257d44633d4a752183ed778b88d2924d0a6b9d`
+
+## Artifacts
+
+- GGUF: `fresh\out\gguf\HRM-Text-1B-BF16.gguf`
+- GGUF SHA256: `2DD5E2EF55E40C46DB0D0CB4CF1427A4E72DA34FEE36F0D2B73D081D0E1C2010`
+- Baseline report: `fresh\reports\validation\baseline_transformers.json`
+- Tensor validation: `fresh\reports\validation\bf16_tensor_validation.json`
+- Runtime validation: `fresh\reports\validation\bf16_vs_hf.json`
+
+Q8_0 quantization was intentionally skipped.
+
+## Commands
+
+```powershell
+python fresh\tools\baseline_transformers.py --model-dir fresh\models\hf\HRM-Text-1B --out fresh\reports\validation\baseline_transformers.json --hf-modules-cache fresh\cache\hf_modules --threads 4
+
+python fresh\third_party\llama.cpp\convert_hf_to_gguf.py fresh\models\hf\HRM-Text-1B --outfile fresh\out\gguf\HRM-Text-1B-BF16.gguf --outtype bf16 --model-name HRM-Text-1B
+
+cmd.exe /c "call ""C:\Program Files\Microsoft Visual Studio\18\Community\Common7\Tools\VsDevCmd.bat"" -arch=x64 -host_arch=x64 && cmake --build build-hrm-nmake --target llama-cli llama-completion llama-results"
+
+python fresh\tools\validate_gguf_tensors.py --hf-dir fresh\models\hf\HRM-Text-1B --gguf fresh\out\gguf\HRM-Text-1B-BF16.gguf --out fresh\reports\validation\bf16_tensor_validation.json
+
+python fresh\tools\validate_bf16_runtime.py --hf-dir fresh\models\hf\HRM-Text-1B --gguf fresh\out\gguf\HRM-Text-1B-BF16.gguf --llama-results fresh\third_party\llama.cpp\build-hrm-nmake\bin\llama-results.exe --llama-completion fresh\third_party\llama.cpp\build-hrm-nmake\bin\llama-completion.exe --out fresh\reports\validation\bf16_vs_hf.json --work-dir fresh\reports\validation\runtime_tmp --hf-modules-cache fresh\cache\hf_modules --threads 4 --n-generate 32 --hf-dtype float32
+```
+
+## Results
+
+- Build: pass.
+- Tensor validation: pass. 259/259 tensors found and compared; BF16 tensor bits match HF after expected BF16 conversion.
+- Runtime validation: pass. Prompt token IDs match for all prompts. Next-token top-1 matches 4/4 prompts. Top-10 overlap is 10/10 for all prompts.
+- Full-vocab mean absolute logit error:
+  - `The quick brown fox`: `0.0199148655`
+  - `In a distant future, humanity`: `0.0051696529`
+  - `Question: What is 2+2?\nAnswer:`: `0.0076530445`
+  - `def fibonacci(n):`: `0.0045031775`
+- Text validation: pass. The BF16 GGUF continuations are aligned with the Transformers baseline. Existing repetition is inherited from the source model, not introduced by conversion.
+
+The runtime comparison uses HF weights loaded as Float32 from the BF16 checkpoint, matching llama.cpp CPU behavior: BF16-stored weights with Float32 compute/accumulation.

runtime/llama.cpp-hrm_text.patch

@@ -0,0 +1,556 @@
+diff --git a/conversion/__init__.py b/conversion/__init__.py
+index 2c38123df..ecf1be2db 100644
+--- a/conversion/__init__.py
++++ b/conversion/__init__.py
+@@ -95,6 +95,7 @@ TEXT_MODEL_MAP: dict[str, str] = {
+     "HunYuanDenseV1ForCausalLM": "hunyuan",
+     "HunYuanMoEV1ForCausalLM": "hunyuan",
+     "HunYuanVLForConditionalGeneration": "hunyuan",
++    "HrmTextForCausalLM": "hrm_text",
+     "IQuestCoderForCausalLM": "llama",
+     "InternLM2ForCausalLM": "internlm",
+     "InternLM3ForCausalLM": "internlm",
+diff --git a/conversion/hrm_text.py b/conversion/hrm_text.py
+new file mode 100644
+index 000000000..1f29ab55e
+--- /dev/null
++++ b/conversion/hrm_text.py
+@@ -0,0 +1,120 @@
++from __future__ import annotations
++
++import re
++import json
++
++from typing import Iterable, TYPE_CHECKING
++
++import torch
++
++if TYPE_CHECKING:
++    from torch import Tensor
++
++from .base import ModelBase, TextModel, gguf, logger
++
++
++@ModelBase.register("HrmTextForCausalLM")
++class HrmTextModel(TextModel):
++    model_arch = gguf.MODEL_ARCH.HRM_TEXT
++
++    def __init__(self, *args, **kwargs):
++        super().__init__(*args, **kwargs)
++
++        with open(self.dir_model / "config.json", "r", encoding="utf-8") as f:
++            self.raw_hparams = json.load(f)
++
++        self.layers_per_stack = self.raw_hparams["num_hidden_layers"]
++        self.h_cycles = self.raw_hparams["H_cycles"]
++        self.l_cycles = self.raw_hparams["L_cycles"]
++        self.physical_block_count = self.layers_per_stack * 2
++        self.cache_block_count = self.layers_per_stack * self.h_cycles * (self.l_cycles + 1)
++
++        # GGUF tensors store one physical L stack followed by one physical H stack.
++        # The runtime expands these 32 physical layers across 128 KV-cache slots.
++        self.block_count = self.physical_block_count
++        self.tensor_map = gguf.get_tensor_name_map(self.model_arch, self.block_count)
++
++    def set_vocab(self):
++        # HRM-Text ships a Qwen2-style tokenizer.json. Keep it as a plain tokenizer;
++        # do not add a chat template for validation GGUFs.
++        self._set_vocab_gpt2()
++
++    def get_vocab_base_pre(self, tokenizer) -> str:
++        del tokenizer
++        return "qwen2"
++
++    def set_gguf_parameters(self):
++        hp = self.raw_hparams
++        head_dim = hp["head_dim"]
++
++        self.gguf_writer.add_context_length(hp["max_position_embeddings"])
++        self.gguf_writer.add_embedding_length(hp["hidden_size"])
++        self.gguf_writer.add_block_count(self.cache_block_count)
++        self.gguf_writer.add_feed_forward_length(hp["intermediate_size"])
++        self.gguf_writer.add_head_count(hp["num_attention_heads"])
++        self.gguf_writer.add_head_count_kv(hp["num_key_value_heads"])
++        self.gguf_writer.add_key_length(head_dim)
++        self.gguf_writer.add_value_length(head_dim)
++        self.gguf_writer.add_rope_dimension_count(head_dim)
++        self.gguf_writer.add_rope_freq_base(hp.get("rope_theta", 10000.0))
++        self.gguf_writer.add_layer_norm_rms_eps(hp["rms_norm_eps"])
++        self.gguf_writer.add_embedding_scale(hp["embedding_scale"])
++
++        arch = self.gguf_writer.arch
++        self.gguf_writer.add_uint32(gguf.Keys.LLM.HRM_LAYERS_PER_STACK.format(arch=arch), self.layers_per_stack)
++        self.gguf_writer.add_uint32(gguf.Keys.LLM.HRM_H_CYCLES.format(arch=arch), self.h_cycles)
++        self.gguf_writer.add_uint32(gguf.Keys.LLM.HRM_L_CYCLES.format(arch=arch), self.l_cycles)
++        self.gguf_writer.add_bool(gguf.Keys.LLM.HRM_PREFIX_LM.format(arch=arch), bool(hp.get("prefix_lm", False)))
++
++    def _format(self, key: gguf.MODEL_TENSOR, bid: int | None = None, suffix: str = ".weight") -> str:
++        return self.format_tensor_name(key, bid=bid, suffix=suffix)
++
++    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:
++        if name == "model.embed_tokens.weight":
++            yield self._format(gguf.MODEL_TENSOR.TOKEN_EMBD), data_torch
++            return
++
++        if name == "lm_head.weight":
++            yield self._format(gguf.MODEL_TENSOR.OUTPUT), data_torch
++            return
++
++        if name == "model.z_L_init":
++            yield self._format(gguf.MODEL_TENSOR.HRM_Z_L_INIT, suffix=""), data_torch
++            return
++
++        match = re.fullmatch(r"model\.([LH])_module\.layers\.(\d+)\.(.+)", name)
++        if match is None:
++            raise ValueError(f"Can not map tensor {name!r}")
++
++        stack, layer_s, tensor_name = match.groups()
++        layer_idx = int(layer_s)
++        if layer_idx >= self.layers_per_stack:
++            raise ValueError(f"Layer index {layer_idx} outside HRM stack size {self.layers_per_stack}")
++
++        physical_bid = layer_idx + (self.layers_per_stack if stack == "H" else 0)
++
++        if tensor_name == "attn.gqkv_proj.weight":
++            gate, q, k, v = torch.chunk(data_torch, 4, dim=0)
++            logger.debug("Split %s as gate, q, k, v", name)
++            yield self._format(gguf.MODEL_TENSOR.ATTN_GATE, physical_bid), gate.contiguous()
++            yield self._format(gguf.MODEL_TENSOR.ATTN_Q, physical_bid), q.contiguous()
++            yield self._format(gguf.MODEL_TENSOR.ATTN_K, physical_bid), k.contiguous()
++            yield self._format(gguf.MODEL_TENSOR.ATTN_V, physical_bid), v.contiguous()
++            return
++
++        if tensor_name == "attn.o_proj.weight":
++            yield self._format(gguf.MODEL_TENSOR.ATTN_OUT, physical_bid), data_torch
++            return
++
++        if tensor_name == "mlp.gate_up_proj.weight":
++            gate, up = torch.chunk(data_torch, 2, dim=0)
++            logger.debug("Split %s as gate, up", name)
++            yield self._format(gguf.MODEL_TENSOR.FFN_GATE, physical_bid), gate.contiguous()
++            yield self._format(gguf.MODEL_TENSOR.FFN_UP, physical_bid), up.contiguous()
++            return
++
++        if tensor_name == "mlp.down_proj.weight":
++            yield self._format(gguf.MODEL_TENSOR.FFN_DOWN, physical_bid), data_torch
++            return
++
++        raise ValueError(f"Can not map tensor {name!r}")
+diff --git a/gguf-py/gguf/constants.py b/gguf-py/gguf/constants.py
+index 7fdcf03d7..b84cc8827 100644
+--- a/gguf-py/gguf/constants.py
++++ b/gguf-py/gguf/constants.py
+@@ -144,6 +144,10 @@ class Keys:
+         TOKEN_SHIFT_COUNT                 = "{arch}.token_shift_count"
+         INTERLEAVE_MOE_LAYER_STEP         = "{arch}.interleave_moe_layer_step"
+         FULL_ATTENTION_INTERVAL           = "{arch}.full_attention_interval"
++        HRM_LAYERS_PER_STACK              = "{arch}.layers_per_stack"
++        HRM_H_CYCLES                      = "{arch}.h_cycles"
++        HRM_L_CYCLES                      = "{arch}.l_cycles"
++        HRM_PREFIX_LM                     = "{arch}.prefix_lm"
+         ACTIVATION_SPARSITY_SCALE         = "{arch}.activation_sparsity_scale"
+         ALTUP_ACTIVE_IDX                  = "{arch}.altup.active_idx"
+         ALTUP_NUM_INPUTS                  = "{arch}.altup.num_inputs"
+@@ -410,6 +414,7 @@ class MODEL_ARCH(IntEnum):
+     QWEN3            = auto()
+     QWEN3MOE         = auto()
+     QWEN3NEXT        = auto()
++    HRM_TEXT         = auto()
+     QWEN3VL          = auto()
+     QWEN3VLMOE       = auto()
+     QWEN35           = auto()
+@@ -527,6 +532,7 @@ class MODEL_TENSOR(IntEnum):
+     TOKEN_TYPES          = auto()
+     POS_EMBD             = auto()
+     OUTPUT               = auto()
++    HRM_Z_L_INIT         = auto()
+     DENSE_2_OUT          = auto() # embeddinggemma 2_Dense
+     DENSE_3_OUT          = auto() # embeddinggemma 3_Dense
+     OUTPUT_NORM          = auto()
+@@ -925,6 +931,7 @@ MODEL_ARCH_NAMES: dict[MODEL_ARCH, str] = {
+     MODEL_ARCH.QWEN3:            "qwen3",
+     MODEL_ARCH.QWEN3MOE:         "qwen3moe",
+     MODEL_ARCH.QWEN3NEXT:        "qwen3next",
++    MODEL_ARCH.HRM_TEXT:         "hrm_text",
+     MODEL_ARCH.QWEN3VL:          "qwen3vl",
+     MODEL_ARCH.QWEN3VLMOE:       "qwen3vlmoe",
+     MODEL_ARCH.QWEN35:           "qwen35",
+@@ -1042,6 +1049,7 @@ TENSOR_NAMES: dict[MODEL_TENSOR, str] = {
+     MODEL_TENSOR.POS_EMBD:                  "position_embd",
+     MODEL_TENSOR.OUTPUT_NORM:               "output_norm",
+     MODEL_TENSOR.OUTPUT:                    "output",
++    MODEL_TENSOR.HRM_Z_L_INIT:              "hrm.z_l_init",
+     MODEL_TENSOR.DENSE_2_OUT:                "dense_2", # embeddinggemma 2_Dense
+     MODEL_TENSOR.DENSE_3_OUT:                "dense_3", # embeddinggemma 2_Dense
+     MODEL_TENSOR.ROPE_FREQS:                "rope_freqs",
+@@ -2057,6 +2065,19 @@ MODEL_TENSORS: dict[MODEL_ARCH, list[MODEL_TENSOR]] = {
+         MODEL_TENSOR.SSM_BETA_ALPHA,
+         MODEL_TENSOR.SSM_OUT
+     ],
++    MODEL_ARCH.HRM_TEXT: [
++        MODEL_TENSOR.TOKEN_EMBD,
++        MODEL_TENSOR.OUTPUT,
++        MODEL_TENSOR.HRM_Z_L_INIT,
++        MODEL_TENSOR.ATTN_Q,
++        MODEL_TENSOR.ATTN_K,
++        MODEL_TENSOR.ATTN_V,
++        MODEL_TENSOR.ATTN_GATE,
++        MODEL_TENSOR.ATTN_OUT,
++        MODEL_TENSOR.FFN_GATE,
++        MODEL_TENSOR.FFN_DOWN,
++        MODEL_TENSOR.FFN_UP,
++    ],
+     MODEL_ARCH.QWEN3VL: [
+         MODEL_TENSOR.TOKEN_EMBD,
+         MODEL_TENSOR.OUTPUT_NORM,
+diff --git a/src/llama-arch.cpp b/src/llama-arch.cpp
+index c9eead18a..5b8ee3781 100644
+--- a/src/llama-arch.cpp
++++ b/src/llama-arch.cpp
+@@ -37,6 +37,7 @@ static const std::map<llm_arch, const char *> LLM_ARCH_NAMES = {
+     { LLM_ARCH_QWEN3,            "qwen3"            },
+     { LLM_ARCH_QWEN3MOE,         "qwen3moe"         },
+     { LLM_ARCH_QWEN3NEXT,        "qwen3next"        },
++    { LLM_ARCH_HRM_TEXT,         "hrm_text"         },
+     { LLM_ARCH_QWEN3VL,          "qwen3vl"          },
+     { LLM_ARCH_QWEN3VLMOE,       "qwen3vlmoe"       },
+     { LLM_ARCH_QWEN35,           "qwen35"           },
+@@ -209,6 +210,10 @@ static const std::map<llm_kv, const char *> LLM_KV_NAMES = {
+     { LLM_KV_TOKEN_SHIFT_COUNT,                 "%s.token_shift_count"                 },
+     { LLM_KV_INTERLEAVE_MOE_LAYER_STEP,         "%s.interleave_moe_layer_step"         },
+     { LLM_KV_FULL_ATTENTION_INTERVAL,           "%s.full_attention_interval"           },
++    { LLM_KV_HRM_LAYERS_PER_STACK,              "%s.layers_per_stack"                  },
++    { LLM_KV_HRM_H_CYCLES,                      "%s.h_cycles"                          },
++    { LLM_KV_HRM_L_CYCLES,                      "%s.l_cycles"                          },
++    { LLM_KV_HRM_PREFIX_LM,                     "%s.prefix_lm"                         },
+ 
+     { LLM_KV_ATTENTION_HEAD_COUNT,                   "%s.attention.head_count"                   },
+     { LLM_KV_ATTENTION_HEAD_COUNT_KV,                "%s.attention.head_count_kv"                },
+@@ -346,6 +351,7 @@ static const std::map<llm_tensor, const char *> LLM_TENSOR_NAMES = {
+     { LLM_TENSOR_OUTPUT_NORM,                            "output_norm" },
+     { LLM_TENSOR_OUTPUT_NORM_LFM2,                       "token_embd_norm" }, // fix for wrong tensor name
+     { LLM_TENSOR_OUTPUT,                                 "output" },
++    { LLM_TENSOR_HRM_Z_L_INIT,                           "hrm.z_l_init" },
+     { LLM_TENSOR_ROPE_FREQS,                             "rope_freqs" },
+     { LLM_TENSOR_ATTN_NORM,                              "blk.%d.attn_norm" },
+     { LLM_TENSOR_ATTN_Q,                                 "blk.%d.attn_q" },
+@@ -565,6 +571,7 @@ static const std::map<llm_tensor, llm_tensor_info> LLM_TENSOR_INFOS = {
+     {LLM_TENSOR_POS_EMBD,                   {LLM_TENSOR_LAYER_INPUT,     GGML_OP_GET_ROWS}},
+     {LLM_TENSOR_TOKEN_TYPES,                {LLM_TENSOR_LAYER_INPUT,     GGML_OP_GET_ROWS}},
+     {LLM_TENSOR_TOKEN_EMBD_NORM,            {LLM_TENSOR_LAYER_REPEATING, GGML_OP_MUL}},  // do the norms on the first layer (not the input layer)
++    {LLM_TENSOR_HRM_Z_L_INIT,               {LLM_TENSOR_LAYER_INPUT,     GGML_OP_MUL}},
+     {LLM_TENSOR_OUTPUT,                     {LLM_TENSOR_LAYER_OUTPUT,    GGML_OP_MUL_MAT}},
+     {LLM_TENSOR_CLS,                        {LLM_TENSOR_LAYER_OUTPUT,    GGML_OP_MUL_MAT}},
+     {LLM_TENSOR_CLS_OUT,                    {LLM_TENSOR_LAYER_OUTPUT,    GGML_OP_MUL_MAT}},
+diff --git a/src/llama-arch.h b/src/llama-arch.h
+index 89cf16cc3..fa04b684b 100644
+--- a/src/llama-arch.h
++++ b/src/llama-arch.h
+@@ -41,6 +41,7 @@ enum llm_arch {
+     LLM_ARCH_QWEN3,
+     LLM_ARCH_QWEN3MOE,
+     LLM_ARCH_QWEN3NEXT,
++    LLM_ARCH_HRM_TEXT,
+     LLM_ARCH_QWEN3VL,
+     LLM_ARCH_QWEN3VLMOE,
+     LLM_ARCH_QWEN35,
+@@ -213,6 +214,10 @@ enum llm_kv {
+     LLM_KV_TOKEN_SHIFT_COUNT,
+     LLM_KV_INTERLEAVE_MOE_LAYER_STEP,
+     LLM_KV_FULL_ATTENTION_INTERVAL,
++    LLM_KV_HRM_LAYERS_PER_STACK,
++    LLM_KV_HRM_H_CYCLES,
++    LLM_KV_HRM_L_CYCLES,
++    LLM_KV_HRM_PREFIX_LM,
+ 
+     LLM_KV_ATTENTION_HEAD_COUNT,
+     LLM_KV_ATTENTION_HEAD_COUNT_KV,
+@@ -354,6 +359,7 @@ enum llm_tensor {
+     LLM_TENSOR_DENSE_2_OUT,
+     LLM_TENSOR_DENSE_3_OUT,
+     LLM_TENSOR_OUTPUT,
++    LLM_TENSOR_HRM_Z_L_INIT,
+     LLM_TENSOR_OUTPUT_NORM,
+     LLM_TENSOR_OUTPUT_NORM_LFM2, // fix for wrong tensor name
+     LLM_TENSOR_ROPE_FREQS,
+diff --git a/src/llama-context.cpp b/src/llama-context.cpp
+index ad36c0666..fa80f4260 100644
+--- a/src/llama-context.cpp
++++ b/src/llama-context.cpp
+@@ -2208,6 +2208,9 @@ uint32_t llama_context::graph_max_nodes(uint32_t n_tokens) const {
+     if (model.arch == LLM_ARCH_QWEN3NEXT || model.arch == LLM_ARCH_KIMI_LINEAR || model.arch == LLM_ARCH_QWEN35 || model.arch == LLM_ARCH_QWEN35MOE) {
+         return std::max<uint32_t>(n_tokens * 40, 32u * model.n_tensors());
+     }
++    if (model.arch == LLM_ARCH_HRM_TEXT) {
++        return std::max<uint32_t>(n_tokens * 80, 64u * model.n_tensors());
++    }
+     uint32_t res = std::max<uint32_t>(1024u, 8u*model.n_tensors());
+     for (const auto & lora : model.loras) {
+         res += lora->get_n_nodes();
+diff --git a/src/llama-hparams.h b/src/llama-hparams.h
+index e2d051edc..812598f69 100644
+--- a/src/llama-hparams.h
++++ b/src/llama-hparams.h
+@@ -164,6 +164,12 @@ struct llama_hparams {
+     float f_embedding_scale = 0.0f;
+     float f_attention_scale = 0.0f;
+ 
++    // HRM-Text recurrence metadata. n_layer remains the expanded KV-cache slot count.
++    uint32_t n_hrm_layer_per_stack = 0;
++    uint32_t n_hrm_h_cycles        = 0;
++    uint32_t n_hrm_l_cycles        = 0;
++    bool     hrm_prefix_lm         = false;
++
+     // grok-2
+     float    f_attn_out_scale = 0.0f;
+     uint32_t attn_temp_length = 0;
+diff --git a/src/llama-model-saver.cpp b/src/llama-model-saver.cpp
+index 528e4c9c0..8a6e009c6 100644
+--- a/src/llama-model-saver.cpp
++++ b/src/llama-model-saver.cpp
+@@ -245,6 +245,10 @@ void llama_model_saver::add_kv_from_model() {
+     add_kv(LLM_KV_TOKEN_SHIFT_COUNT,                 hparams.token_shift_count);
+     add_kv(LLM_KV_INTERLEAVE_MOE_LAYER_STEP,         hparams.n_moe_layer_step);
+     // add_kv(LLM_KV_FULL_ATTENTION_INTERVAL,           ???);
++    add_kv(LLM_KV_HRM_LAYERS_PER_STACK,              hparams.n_hrm_layer_per_stack);
++    add_kv(LLM_KV_HRM_H_CYCLES,                      hparams.n_hrm_h_cycles);
++    add_kv(LLM_KV_HRM_L_CYCLES,                      hparams.n_hrm_l_cycles);
++    add_kv(LLM_KV_HRM_PREFIX_LM,                     hparams.hrm_prefix_lm);
+ 
+     add_kv(LLM_KV_ATTENTION_HEAD_COUNT,              hparams.n_head_arr, true);
+     add_kv(LLM_KV_ATTENTION_HEAD_COUNT_KV,           hparams.n_head_kv_arr, true);
+diff --git a/src/llama-model.cpp b/src/llama-model.cpp
+index 8bf20a716..a3cc996aa 100644
+--- a/src/llama-model.cpp
++++ b/src/llama-model.cpp
+@@ -96,6 +96,8 @@ static llama_model * llama_model_mapping(llm_arch arch, const llama_model_params
+             return new llama_model_qwen2moe(params);
+         case LLM_ARCH_QWEN3:
+             return new llama_model_qwen3(params);
++        case LLM_ARCH_HRM_TEXT:
++            return new llama_model_hrm_text(params);
+         case LLM_ARCH_QWEN3MOE:
+             return new llama_model_qwen3moe(params);
+         case LLM_ARCH_QWEN3VL:
+@@ -2339,6 +2341,7 @@ llama_rope_type llama_model_rope_type(const llama_model * model) {
+         case LLM_ARCH_PANGU_EMBED:
+         case LLM_ARCH_AFMOE:
+         case LLM_ARCH_QWEN3NEXT:
++        case LLM_ARCH_HRM_TEXT:
+         case LLM_ARCH_MIMO2:
+         case LLM_ARCH_STEP35:
+             return LLAMA_ROPE_TYPE_NEOX;
+diff --git a/src/models/hrm-text.cpp b/src/models/hrm-text.cpp
+new file mode 100644
+index 000000000..e0a3e9f59
+--- /dev/null
++++ b/src/models/hrm-text.cpp
+@@ -0,0 +1,183 @@
++#include "models.h"
++
++#include <cmath>
++#include <vector>
++
++void llama_model_hrm_text::load_arch_hparams(llama_model_loader & ml) {
++    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
++    ml.get_key(LLM_KV_EMBEDDING_SCALE,             hparams.f_embedding_scale);
++    ml.get_key(LLM_KV_HRM_LAYERS_PER_STACK,        hparams.n_hrm_layer_per_stack);
++    ml.get_key(LLM_KV_HRM_H_CYCLES,                hparams.n_hrm_h_cycles);
++    ml.get_key(LLM_KV_HRM_L_CYCLES,                hparams.n_hrm_l_cycles);
++    ml.get_key(LLM_KV_HRM_PREFIX_LM,               hparams.hrm_prefix_lm, false);
++
++    switch (hparams.n_embd) {
++        case 1536: type = LLM_TYPE_1B; break;
++        default:   type = LLM_TYPE_UNKNOWN;
++    }
++}
++
++void llama_model_hrm_text::load_arch_tensors(llama_model_loader &) {
++    LLAMA_LOAD_LOCALS;
++
++    const int64_t n_stack = hparams.n_hrm_layer_per_stack;
++    const int64_t n_cycle_slots = n_stack * (hparams.n_hrm_l_cycles + 1);
++
++    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);
++    output   = create_tensor(tn(LLM_TENSOR_OUTPUT,     "weight"), {n_embd, n_vocab}, 0);
++
++    hrm_z_l_init = create_tensor(tn(LLM_TENSOR_HRM_Z_L_INIT), {n_embd}, 0);
++
++    std::vector<bool> loaded_physical(2 * n_stack, false);
++
++    for (int il = 0; il < n_layer; ++il) {
++        auto & layer = layers[il];
++
++        const int64_t layer_in_stack = il % n_stack;
++        const int64_t phase = (il % n_cycle_slots) / n_stack;
++        const bool is_h_stack = phase == int64_t(hparams.n_hrm_l_cycles);
++        const int physical_bid = int((is_h_stack ? n_stack : 0) + layer_in_stack);
++
++        const int flags = loaded_physical[physical_bid] ? TENSOR_DUPLICATED : 0;
++        loaded_physical[physical_bid] = true;
++
++        create_tensor_qkv(layer, physical_bid,
++                n_embd,
++                n_embd_head_k * n_head,
++                n_embd_k_gqa,
++                n_embd_v_gqa,
++                flags);
++
++        layer.wqkv_gate = create_tensor(tn(LLM_TENSOR_ATTN_GATE, "weight", physical_bid), {n_embd, n_embd_head_k * n_head}, flags);
++        layer.wo        = create_tensor(tn(LLM_TENSOR_ATTN_OUT,  "weight", physical_bid), {n_embd_head_k * n_head, n_embd}, flags);
++
++        layer.ffn_gate = create_tensor(tn(LLM_TENSOR_FFN_GATE, "weight", physical_bid), {n_embd, n_ff}, flags);
++        layer.ffn_down = create_tensor(tn(LLM_TENSOR_FFN_DOWN, "weight", physical_bid), {n_ff, n_embd}, flags);
++        layer.ffn_up   = create_tensor(tn(LLM_TENSOR_FFN_UP,   "weight", physical_bid), {n_embd, n_ff}, flags);
++    }
++}
++
++std::unique_ptr<llm_graph_context> llama_model_hrm_text::build_arch_graph(const llm_graph_params & params) const {
++    return std::make_unique<graph>(*this, params);
++}
++
++llama_model_hrm_text::graph::graph(const llama_model & model_, const llm_graph_params & params) : llm_graph_context(params) {
++    const auto & model = static_cast<const llama_model_hrm_text &>(model_);
++
++    GGML_ASSERT(model.tok_embd != nullptr);
++    GGML_ASSERT(model.output != nullptr);
++    GGML_ASSERT(model.hrm_z_l_init != nullptr);
++
++    const int64_t n_embd_head = hparams.n_embd_head_v();
++    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k());
++    GGML_ASSERT(n_embd_head == n_rot);
++
++    const int64_t n_stack = hparams.n_hrm_layer_per_stack;
++    const int64_t h_cycles = hparams.n_hrm_h_cycles;
++    const int64_t l_cycles = hparams.n_hrm_l_cycles;
++
++    ggml_tensor * inp_pos = build_inp_pos();
++    auto * inp_attn = build_attn_inp_kv();
++    ggml_tensor * inp_out_ids = build_inp_out_ids();
++
++    ggml_tensor * hidden_high = build_inp_embd(model.tok_embd);
++    ggml_tensor * hidden_low = ggml_repeat(ctx0, model.hrm_z_l_init, hidden_high);
++    cb(hidden_low, "hrm_z_l_init", -1);
++
++    const float kq_scale = 1.0f / std::sqrt(float(n_embd_head));
++
++    auto build_stack = [&](ggml_tensor * stack_inp, int slot_offset) -> ggml_tensor * {
++        ggml_tensor * stack_cur = stack_inp;
++
++        for (int layer_idx = 0; layer_idx < n_stack; ++layer_idx) {
++            const int il = slot_offset + layer_idx;
++            const auto & layer = model.layers[il];
++
++            ggml_tensor * inpSA = stack_cur;
++            ggml_tensor * cur = build_norm(stack_cur, nullptr, nullptr, LLM_NORM_RMS, il);
++            cb(cur, "attn_norm", il);
++
++            {
++                ggml_tensor * attn_inp = cur;
++                auto [Qcur, Kcur, Vcur] = build_qkv(layer, cur, n_embd_head, n_head, n_head_kv, il);
++
++                ggml_tensor * gate = build_lora_mm(layer.wqkv_gate, attn_inp, layer.wqkv_gate_s);
++                cb(gate, "attn_gate_proj", il);
++
++                Qcur = ggml_rope_ext(
++                        ctx0, Qcur, inp_pos, nullptr,
++                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
++                        ext_factor, attn_factor, beta_fast, beta_slow);
++                cb(Qcur, "Qcur_rope", il);
++
++                Kcur = ggml_rope_ext(
++                        ctx0, Kcur, inp_pos, nullptr,
++                        n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,
++                        ext_factor, attn_factor, beta_fast, beta_slow);
++                cb(Kcur, "Kcur_rope", il);
++
++                cur = build_attn(inp_attn,
++                        nullptr, nullptr, nullptr,
++                        Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
++                cb(cur, "attn_out", il);
++
++                gate = ggml_sigmoid(ctx0, gate);
++                cb(gate, "attn_gate_sig", il);
++
++                cur = ggml_mul(ctx0, cur, gate);
++                cb(cur, "attn_gated", il);
++
++                cur = build_lora_mm(layer.wo, cur, layer.wo_s);
++                cb(cur, "attn_o_proj", il);
++            }
++
++            ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
++            cb(ffn_inp, "ffn_inp", il);
++
++            cur = build_norm(ffn_inp, nullptr, nullptr, LLM_NORM_RMS, il);
++            cb(cur, "ffn_norm", il);
++
++            cur = build_ffn(cur,
++                    layer.ffn_up,   nullptr, layer.ffn_up_s,
++                    layer.ffn_gate, nullptr, layer.ffn_gate_s,
++                    layer.ffn_down, nullptr, layer.ffn_down_s,
++                    nullptr,
++                    LLM_FFN_SILU, LLM_FFN_PAR, il);
++            cb(cur, "ffn_out", il);
++
++            cur = ggml_add(ctx0, cur, ffn_inp);
++            cur = build_cvec(cur, il);
++            cb(cur, "hrm_layer_out", il);
++
++            stack_cur = cur;
++        }
++
++        stack_cur = build_norm(stack_cur, nullptr, nullptr, LLM_NORM_RMS, slot_offset);
++        cb(stack_cur, "stack_final_norm", slot_offset);
++        return stack_cur;
++    };
++
++    for (int h = 0; h < h_cycles; ++h) {
++        for (int l = 0; l < l_cycles; ++l) {
++            const int slot_offset = int((h * (l_cycles + 1) + l) * n_stack);
++            hidden_low = build_stack(ggml_add(ctx0, hidden_low, hidden_high), slot_offset);
++        }
++
++        const int slot_offset = int((h * (l_cycles + 1) + l_cycles) * n_stack);
++        hidden_high = build_stack(ggml_add(ctx0, hidden_high, hidden_low), slot_offset);
++    }
++
++    ggml_tensor * cur = hidden_high;
++
++    if (inp_out_ids) {
++        cur = ggml_get_rows(ctx0, cur, inp_out_ids);
++    }
++
++    res->t_embd = cur;
++
++    cur = build_lora_mm(model.output, cur, model.output_s);
++    cb(cur, "result_output", -1);
++
++    res->t_logits = cur;
++    ggml_build_forward_expand(gf, cur);
++}
+diff --git a/src/models/models.h b/src/models/models.h
+index 7e551eb96..7da6b7f7f 100644
+--- a/src/models/models.h
++++ b/src/models/models.h
+@@ -515,6 +515,20 @@ struct llama_model_qwen3 : public llama_model_base {
+     std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
+ };
+ 
++struct llama_model_hrm_text : public llama_model_base {
++    llama_model_hrm_text(const struct llama_model_params & params) : llama_model_base(params) {}
++    void load_arch_hparams(llama_model_loader & ml) override;
++    void load_arch_tensors(llama_model_loader & ml) override;
++
++    ggml_tensor * hrm_z_l_init = nullptr;
++
++    struct graph : public llm_graph_context {
++        graph(const llama_model & model, const llm_graph_params & params);
++    };
++
++    std::unique_ptr<llm_graph_context> build_arch_graph(const llm_graph_params & params) const override;
++};
++
+ 
+ struct llama_model_qwen3moe : public llama_model_base {
+     llama_model_qwen3moe(const struct llama_model_params & params) : llama_model_base(params) {}