commit 6aedc7be68ff2cf6c35362146997048c0b90e468 Author: ModelHub XC Date: Mon Oct 12 05:03:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..986f7b9 --- /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-MMMU-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MTM-Merge-MMMU-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MTM-Merge-MMMU-gemma-2-9B.IQ4_XS.gguf b/MTM-Merge-MMMU-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..11ccee8 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83bcfb3ec68699cc949a048998577826279beb3ee2606629ae1e053df01411dc +size 5223172000 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q2_K.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..0ce0359 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:158b258c84453011682a801c1c961710b5e89d6e5f1d756a8e40a74c0cd5f952 +size 3805398944 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q3_K_L.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..839df49 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14995178d303f9b17ce4ab225c021954eec4871000f529ee1c30f673073dfcd2 +size 5132453792 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q3_K_M.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..167cd55 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e9b709f658555512bc48bd638cba1fcb4e07c96b4b145abc6f4ac607a3caa8 +size 4761782176 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q3_K_S.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..2c6c06e --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd89f208110ff6258d8879d8adb0199f4a2237b704836a693932949d4a8dd3b9 +size 4337665952 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q4_K_M.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..b34db46 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4acf1e32397a9ba893150bae9866d614b94c04d19b94f9f83d7d06e7f042446a +size 5761058720 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q4_K_S.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..0b40971 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68c6fbda118a7246fec459c631d5d9df233768df6ad27839a8885fe82f84ce1d +size 5478926240 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q5_K_M.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..97d5c5e --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7ba8fc490a7c902e904ba21baa57c2149640b359685f3b75c655c38dda378f +size 6647367584 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q5_K_S.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..e9633c6 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:125f2a398ee6d77268b43250a5a2e856491575ade1f60780eadbb5f3a14207b9 +size 6483593120 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q6_K.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..1138124 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5868caf2283567a90bd0be0e1996318ab727950c4426f8ea93c1ac22053bfe1e +size 7589070752 diff --git a/MTM-Merge-MMMU-gemma-2-9B.Q8_0.gguf b/MTM-Merge-MMMU-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..e462df6 --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f98357de68d94bf6965ba85a96375549a73189fd27cfacd478c82e6c5abc0fb +size 9827149728 diff --git a/MTM-Merge-MMMU-gemma-2-9B.f16.gguf b/MTM-Merge-MMMU-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..60b5fbf --- /dev/null +++ b/MTM-Merge-MMMU-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5404d0a6217492cf487cca649afd9ed30ac8a968aac9ae640f3dc2d203a2c0e3 +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..767d82e --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MTM-Merge-MMMU-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MTM-Merge-MMMU-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-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MTM-Merge-MMMU-gemma-2-9B-GGUF/resolve/main/MTM-Merge-MMMU-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. + +