Squash history

.gitattributes

@@ -0,0 +1,39 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+humanizer-12b-Q6_K_ROCMFPX.gguf filter=lfs diff=lfs merge=lfs -text
+humanizer-12b-Q8_0_ROCMFPX.gguf filter=lfs diff=lfs merge=lfs -text
+humanizer-12b-Q4_0_ROCMFP4_STRIX.gguf filter=lfs diff=lfs merge=lfs -text
+humanizer-12b-Q4_0_ROCMFP4_FAST.gguf filter=lfs diff=lfs merge=lfs -text

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.

NOTICE

@@ -0,0 +1,10 @@
+humanizer
+Copyright 2026 Stephen Yu
+
+This product is licensed under the Apache License, Version 2.0 (see LICENSE).
+This applies to the code in this repository and to the released model weights.
+
+The model weights are fine-tuned from google/gemma-4-12B
+(https://huggingface.co/google/gemma-4-12B), which Google releases under the
+Apache License, Version 2.0. The previous release in lite/ is fine-tuned from
+google/gemma-4-E4B. This project is not affiliated with or endorsed by Google.

README.md

@@ -0,0 +1,133 @@
+---
+license: apache-2.0
+base_model: jialinyyzz/humanizer
+base_model_relation: quantized
+pipeline_tag: text-generation
+library_name: gguf
+language: [en, zh]
+tags: [gguf, rocmfpx, rocmfp4, amd, rocm, strix-halo, quantized, humanizer, text-rewriting, gemma4]
+---
+
+# humanizer 12B — ROCmFPX GGUF
+
+[jialinyyzz/humanizer](https://huggingface.co/jialinyyzz/humanizer) (v2) rewrites AI-written drafts in English and
+Chinese so they read like a person wrote them, and keeps every number, date, name and quote. It is a fine-tune of
+Gemma 4 12B. This repo has it in the [ROCmFPX](https://github.com/charlie12345/ROCmFPX) formats, a llama.cpp fork
+with low-bit weight types for AMD GPUs (Vulkan and HIP/ROCm).
+
+**Start with `humanizer-12b-Q8_0_ROCMFPX.gguf`** if it fits in your GPU memory: it is almost identical to the full
+model. Take the 6-bit file next, and a 4-bit file when memory is tight.
+
+> These files need [HarshaVardhan3002/ROCmFPX](https://github.com/HarshaVardhan3002/ROCmFPX), built from
+> 23 October 2026 or later (they carry per-tensor scales, see below). Stock llama.cpp, LM Studio, Ollama and other
+> ROCmFPX builds may not load them. **These files have not been tested on AMD hardware yet.**
+>
+> Not an official release of humanizer. All credit for the model goes to its authors. Their own files in stock
+> llama.cpp formats, including quantization-aware trained 2-, 3- and 4-bit files, are at
+> [jialinyyzz/humanizer-GGUF](https://huggingface.co/jialinyyzz/humanizer-GGUF).
+
+## Files
+
+| File | Size | KL to BF16 | Same top token | |
+|---|---:|---:|---:|---|
+| `humanizer-12b-Q8_0_ROCMFPX.gguf` | 12.3 GB | 0.00024 | 99.3% | 8-bit, closest to the full model |
+| `humanizer-12b-Q6_K_ROCMFPX.gguf` | 9.8 GB | 0.0023 | 97.8% | 6-bit (ROCmFPX `Q6_0_ROCMFPX` weights, see below) |
+| `humanizer-12b-Q4_0_ROCMFP4_STRIX.gguf` | 6.7 GB | 0.040 | 91.9% | recommended 4-bit (Strix Halo recipe) |
+| `humanizer-12b-Q4_0_ROCMFP4_FAST.gguf` | 6.3 GB | 0.047 | 90.8% | smallest, speed-first 4-bit |
+
+Stock llama.cpp builds of this model, measured the same way:
+
+| Stock file | Size | KL to BF16 | Same top token |
+|---|---:|---:|---:|
+| Q8_0 | 12.7 GB | 0.00064 | 98.8% |
+| Q6_K | 10.0 GB | 0.0026 | 97.8% |
+| Q4_K_M | 7.4 GB | 0.0186 | 94.1% |
+
+The 8-bit file here is closer to BF16 than a stock Q8_0, and the 6-bit file matches a stock Q6_K; both are a
+little smaller. At 4-bit, a stock Q4_K_M (or the authors' quantization-aware Q4_K_M) stays closer to the full model than the ROCmFP4
+files here. The ROCmFP4 files are smaller and are meant for speed on AMD GPUs.
+
+**How this was measured:** llama.cpp `llama-perplexity --kl-divergence` against the authors' BF16 file, 40 chunks of
+512 tokens of English Wikipedia text (wikitext-2), run on a GPU after expanding each file to F16 (the expansion is
+exact). KL is how far the file's next-token probabilities drift from BF16, averaged over every token; lower is better.
+"Same top token" is how often the file's most likely next token is the same as BF16's. This is general text, not
+rewriting text; the authors measured their files on held-out rewriting data, and their stock Q4_K_M (KL 0.021) is
+close to what this test gives (0.0186).
+
+Every file also passed a rewrite check: a test draft with five facts (a date, a count, a name, a year and an amount),
+greedy decoding on the CPU. All five facts came through in every file.
+
+The 6-bit file is named `humanizer-12b-Q6_K_ROCMFPX.gguf` so that Hugging Face lists it as a 6-bit quant. Its weights
+are the ROCmFPX `Q6_0_ROCMFPX` type, not a stock llama.cpp `Q6_K`, and it needs the same fork as the other files.
+
+## Why these files carry tensor scales
+
+ROCmFPX stores one scale for each block of weights as an 8-bit float (UE4M3) whose smallest step is 2^-10. This
+model's weights are small (the largest value in a typical block of 32 is about 0.02 to 0.04), so an 8-bit ROCmFPX
+file cannot pick small enough scales: almost every block gets stuck at the smallest scale, and the file is about as
+precise as a 6-bit one. These files multiply each weight matrix by a power of two (2^7 to 2^10) before quantizing and store
+the inverse as `<name>.scale`, which the fork multiplies back after the matrix product. The shared embedding and
+output matrix cannot take such a scale, so it uses a stock llama.cpp type: Q8_0 in the 8-bit file, Q6_K in the 6-bit
+and STRIX files (the FAST file keeps it in ROCmFP4 for speed).
+
+| KL to BF16 | Plain ROCmFPX | With tensor scales |
+|---|---:|---:|
+| 8-bit | 0.0112 | 0.00024 |
+| 6-bit | 0.0080 | 0.0023 |
+| 4-bit STRIX | 0.053 | 0.040 |
+| 4-bit FAST | 0.064 | 0.047 |
+
+## How these were made
+
+1. Source: the authors' BF16 GGUF (`humanizer-12b-bf16.gguf` from
+   [jialinyyzz/humanizer-GGUF](https://huggingface.co/jialinyyzz/humanizer-GGUF)), sha256 checked against their card.
+2. Importance matrix from the BF16 file over a general calibration text (`calibration_datav3`), 512-token chunks.
+   The authors used their own rewriting data for theirs.
+3. `llama-quantize --imatrix` from the BF16 file with `LLAMA_ROCMFPX_TENSOR_SCALE=1`, one run per type, from
+   [HarshaVardhan3002/ROCmFPX](https://github.com/HarshaVardhan3002/ROCmFPX); `--token-embedding-type q8_0` for the
+   8-bit file and `q6_K` for the 6-bit file.
+
+The only change from the original is the weight quantization. The tokenizer, the chat template and the stored sampling
+defaults come unchanged from the authors' GGUF.
+
+## Run
+
+```bash
+git clone https://github.com/HarshaVardhan3002/ROCmFPX && cd ROCmFPX
+cmake -B build -DGGML_VULKAN=ON          # or -DGGML_HIP=ON -DAMDGPU_TARGETS=gfx1151 (gfx1100 for RX 7900)
+cmake --build build --target llama-server -j
+build/bin/llama-server -m humanizer-12b-Q8_0_ROCMFPX.gguf -ngl 999 -c 8192 -np 1 --jinja
+```
+
+The model does text completion, not chat. The prompt is the instruction from `prompt_format.json`, a blank line, your
+draft, then `\n\n### Rewritten:\n\n`. Sample with temperature 1.0, top-p 0.95, top-k 0, min-p 0 and repeat penalty 1.0,
+and stop at the end-of-sequence token only.
+
+```python
+import json, urllib.request
+
+pf = json.load(open("prompt_format.json", encoding="utf-8"))
+
+def humanize(draft, url="http://127.0.0.1:8080"):
+    body = {"prompt": pf["instr"] + "\n\n" + draft.strip() + pf["sep"],
+            "temperature": 1.0, "top_p": 0.95, "top_k": 0, "min_p": 0,
+            "repeat_penalty": 1.0, "n_predict": 2048}
+    req = urllib.request.Request(url + "/completion", json.dumps(body).encode("utf-8"),
+                                 {"Content-Type": "application/json"})
+    with urllib.request.urlopen(req, timeout=900) as r:
+        return json.load(r)["content"].strip()
+
+print(humanize(open("draft.txt", encoding="utf-8").read()))
+```
+
+The chat template in each file builds the same prompt from the last user message, so `/v1/chat/completions` with one
+draft per message also works. Keep instruction, draft and rewrite within 8,192 tokens and split long documents at
+paragraph breaks. The authors note that a short, informal English draft occasionally comes back in Chinese; sample
+again when that happens. Their [usage guide](https://github.com/sgaofen/humanizer-local-model/blob/main/docs/USAGE.md)
+has more. Their desktop app runs stock llama.cpp with their own files, not these.
+
+## License
+
+Apache-2.0, same as the original (see `LICENSE`). The authors' `NOTICE` file is included and must stay with any copy.
+humanizer is fine-tuned from [google/gemma-4-12B](https://huggingface.co/google/gemma-4-12B), which Google releases
+under Apache 2.0. This repo is not affiliated with or endorsed by Google or the humanizer authors.

humanizer-12b-Q4_0_ROCMFP4_FAST.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc6d29ddd3247f0bfe52203ac6bc4b5c01842c4e4a00a12cdd72f18bd3a72fb
+size 6344287328

humanizer-12b-Q4_0_ROCMFP4_STRIX.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d5674106101f06e0b716545d19e53bf734b39c45d7727e7348c16ed1d1c5a4
+size 6655419488

humanizer-12b-Q6_K_ROCMFPX.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57614e79ec45e7c8331837991cbffca5b11f4cd7aa4f9ef1e6cb37ac5406cec1
+size 9847964768

humanizer-12b-Q8_0_ROCMFPX.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d6845e89f0c7fef62ff3d1c79fdf85ef3e3b86dcf001d34dadc30b5c1efbb4
+size 12329034848

prompt_format.json

@@ -0,0 +1,8 @@
+{
+ "style": "legacy",
+ "sep": "\n\n### Rewritten:\n\n",
+ "fingerprint": "cc51d66b4c593fbe",
+ "instr": "Rewrite the text below so it reads like a person wrote it, not a language model.\n\nReorganize it as you see fit. Vary sentence length on purpose. Cut hedging,\nthroat-clearing, and any sentence that only announces what comes next.\nPrefer the concrete word over the abstract one. It is fine to sound uneven.\n\nEvery fact, number, unit, date, name and quotation must survive unchanged.",
+ "chat": false,
+ "note": "推理时需 instr + draft + sep"
+}