commit 97a9a874e80b332644dd912a010e4bb914dd1f69 Author: ModelHub XC Date: Sat Oct 10 09:31:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MTM-Merge-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c77983 --- /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 +MTM-Merge-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MTM-Merge-gemma-2-9B.IQ4_XS.gguf b/MTM-Merge-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..7229a0e --- /dev/null +++ b/MTM-Merge-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81d476f2e6e90a1e7920d0a85cce52b057bd69ba2fedc7ed68d283e7672a6ac +size 5223172000 diff --git a/MTM-Merge-gemma-2-9B.Q2_K.gguf b/MTM-Merge-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..1e50c94 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e2c994f24d8c05b8e7627f3eb374f9017babb47d3cb5c03f4bbc7bd54826ca +size 3805398944 diff --git a/MTM-Merge-gemma-2-9B.Q3_K_L.gguf b/MTM-Merge-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..c14227c --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b129334909eedc2b5a4a14f20c8afdc29ccdc076844e0f811041fa70fc5f317 +size 5132453792 diff --git a/MTM-Merge-gemma-2-9B.Q3_K_M.gguf b/MTM-Merge-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..903aa80 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beba1d967c405186a6934263fa20976af1bf629268726ff96814d6a97cabfc2b +size 4761782176 diff --git a/MTM-Merge-gemma-2-9B.Q3_K_S.gguf b/MTM-Merge-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..4cb7ddf --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223825f721ffcdac5e8e23402f78acb8b89ffc8c679d36575ac837ad083c909e +size 4337665952 diff --git a/MTM-Merge-gemma-2-9B.Q4_K_M.gguf b/MTM-Merge-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..abcb130 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22336815d8049cb86e6ddce4ead4d095484a1a46f0851d76ca6650ff207dc09f +size 5761058720 diff --git a/MTM-Merge-gemma-2-9B.Q4_K_S.gguf b/MTM-Merge-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..b873dff --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18cd2dd345504f07c50331f4155c0f5b57b150475f13a84b0162772c30935c73 +size 5478926240 diff --git a/MTM-Merge-gemma-2-9B.Q5_K_M.gguf b/MTM-Merge-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..e158256 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68131cac037af84fb25c599ec1d3d7278c829678009733b590c37bfaf30dbb59 +size 6647367584 diff --git a/MTM-Merge-gemma-2-9B.Q5_K_S.gguf b/MTM-Merge-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..1c7ec8c --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b75fab470ad888a0bb2a79307ad0f67de98efbb08fafe2d9c31c83f4e9f047c +size 6483593120 diff --git a/MTM-Merge-gemma-2-9B.Q6_K.gguf b/MTM-Merge-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..cbe9e47 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15375b72456d0d650d4f72be421694fe89eadfd066f7cf4add9f6491bfea9e21 +size 7589070752 diff --git a/MTM-Merge-gemma-2-9B.Q8_0.gguf b/MTM-Merge-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..871d226 --- /dev/null +++ b/MTM-Merge-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43cdd2f01d7c17cc89e7b15d011961a8f1ceff7d74cb489e047a94e3dd69cb52 +size 9827149728 diff --git a/MTM-Merge-gemma-2-9B.f16.gguf b/MTM-Merge-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..7acad3e --- /dev/null +++ b/MTM-Merge-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79affc2b3901c95d990c24e6400291046aba20cc87577532919f254795f4e603 +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8969b3 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: zelk12/MTM-Merge-gemma-2-9B +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MTM-Merge-gemma-2-9B + + +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/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-gemma-2-9B-GGUF/resolve/main/MTM-Merge-gemma-2-9B.f16.gguf) | f16 | 18.6 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +