From fabc90c1de044e54c7bd97627e22066128b2325c Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Wed, 15 Jul 2026 08:20:09 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/JudgeLRM-4B-GGUF Source: Original Platform --- .gitattributes | 47 +++++++++++++++++++++++++++ JudgeLRM-4B.IQ4_XS.gguf | 3 ++ JudgeLRM-4B.Q2_K.gguf | 3 ++ JudgeLRM-4B.Q3_K_L.gguf | 3 ++ JudgeLRM-4B.Q3_K_M.gguf | 3 ++ JudgeLRM-4B.Q3_K_S.gguf | 3 ++ JudgeLRM-4B.Q4_K_M.gguf | 3 ++ JudgeLRM-4B.Q4_K_S.gguf | 3 ++ JudgeLRM-4B.Q5_K_M.gguf | 3 ++ JudgeLRM-4B.Q5_K_S.gguf | 3 ++ JudgeLRM-4B.Q6_K.gguf | 3 ++ JudgeLRM-4B.Q8_0.gguf | 3 ++ JudgeLRM-4B.f16.gguf | 3 ++ README.md | 71 +++++++++++++++++++++++++++++++++++++++++ 14 files changed, 154 insertions(+) create mode 100644 .gitattributes create mode 100644 JudgeLRM-4B.IQ4_XS.gguf create mode 100644 JudgeLRM-4B.Q2_K.gguf create mode 100644 JudgeLRM-4B.Q3_K_L.gguf create mode 100644 JudgeLRM-4B.Q3_K_M.gguf create mode 100644 JudgeLRM-4B.Q3_K_S.gguf create mode 100644 JudgeLRM-4B.Q4_K_M.gguf create mode 100644 JudgeLRM-4B.Q4_K_S.gguf create mode 100644 JudgeLRM-4B.Q5_K_M.gguf create mode 100644 JudgeLRM-4B.Q5_K_S.gguf create mode 100644 JudgeLRM-4B.Q6_K.gguf create mode 100644 JudgeLRM-4B.Q8_0.gguf create mode 100644 JudgeLRM-4B.f16.gguf create mode 100644 README.md diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..933203a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +JudgeLRM-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +JudgeLRM-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/JudgeLRM-4B.IQ4_XS.gguf b/JudgeLRM-4B.IQ4_XS.gguf new file mode 100644 index 0000000..013ae6c --- /dev/null +++ b/JudgeLRM-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1901a36057c69eae7dec5f27a55874442fd7ae70c51da0aa509bfcc5059a25 +size 2492949312 diff --git a/JudgeLRM-4B.Q2_K.gguf b/JudgeLRM-4B.Q2_K.gguf new file mode 100644 index 0000000..5958141 --- /dev/null +++ b/JudgeLRM-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b965f50586319f46e36ed9140765962eed79edb4128700ad56f8425020533b +size 1797125952 diff --git a/JudgeLRM-4B.Q3_K_L.gguf b/JudgeLRM-4B.Q3_K_L.gguf new file mode 100644 index 0000000..a0f2008 --- /dev/null +++ b/JudgeLRM-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6e1661e0cb72e0df2f84ae335e85a976c79401b9bcc6beb66b7c4ac29ff4a7b +size 2406915392 diff --git a/JudgeLRM-4B.Q3_K_M.gguf b/JudgeLRM-4B.Q3_K_M.gguf new file mode 100644 index 0000000..ed45373 --- /dev/null +++ b/JudgeLRM-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0403a0d2c2d7e23c01b4b50532a82688f17893e35ec5af5a7913f5e99b3657d0 +size 2242747712 diff --git a/JudgeLRM-4B.Q3_K_S.gguf b/JudgeLRM-4B.Q3_K_S.gguf new file mode 100644 index 0000000..39c243d --- /dev/null +++ b/JudgeLRM-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24027c681495f2c0ff2b7aee96c961835781edd1775d01371164212b59096b5c +size 2054126912 diff --git a/JudgeLRM-4B.Q4_K_M.gguf b/JudgeLRM-4B.Q4_K_M.gguf new file mode 100644 index 0000000..f931adc --- /dev/null +++ b/JudgeLRM-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78679772034402d92505870249c6583f50d4a2308cb954342badf66f72a8539 +size 2716068672 diff --git a/JudgeLRM-4B.Q4_K_S.gguf b/JudgeLRM-4B.Q4_K_S.gguf new file mode 100644 index 0000000..5b83247 --- /dev/null +++ b/JudgeLRM-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b0a3d99eb5c1b7d8cf711334f6fb38170d2ca9f57ce6f5fa2258a9f815f7cc6 +size 2602097472 diff --git a/JudgeLRM-4B.Q5_K_M.gguf b/JudgeLRM-4B.Q5_K_M.gguf new file mode 100644 index 0000000..6deb7f6 --- /dev/null +++ b/JudgeLRM-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03e472e788a59da54894a1466115c64961d52d438f227e8e67c276e0f2c9ac96 +size 3156921152 diff --git a/JudgeLRM-4B.Q5_K_S.gguf b/JudgeLRM-4B.Q5_K_S.gguf new file mode 100644 index 0000000..13afb82 --- /dev/null +++ b/JudgeLRM-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b29e3c1133597ccf47f9320c5560c8cf013f6ccea088036d3f15b97902a44519 +size 3091118912 diff --git a/JudgeLRM-4B.Q6_K.gguf b/JudgeLRM-4B.Q6_K.gguf new file mode 100644 index 0000000..812d0a6 --- /dev/null +++ b/JudgeLRM-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7f2b899f827a516e06c04e573c7908231eb8d94ab0cb6ac6fcf2753b0010be6 +size 3625326912 diff --git a/JudgeLRM-4B.Q8_0.gguf b/JudgeLRM-4B.Q8_0.gguf new file mode 100644 index 0000000..378be0d --- /dev/null +++ b/JudgeLRM-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c50cff09c5c3f1682c04eefd8f5d40cbe5d2daf96dc0fcf9a563b9357bc0f94d +size 4693671232 diff --git a/JudgeLRM-4B.f16.gguf b/JudgeLRM-4B.f16.gguf new file mode 100644 index 0000000..9f0197c --- /dev/null +++ b/JudgeLRM-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4cdd596354b3088e506e0ca7f02fd07758c000d946485c340f6547e35d49c3b +size 8829197632 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d1b810 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: anonymous-D1C4/DECIDE-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/anonymous-D1C4/DECIDE-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#JudgeLRM-4B-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/JudgeLRM-4B-GGUF/resolve/main/JudgeLRM-4B.f16.gguf) | f16 | 8.9 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +