commit 7b8a87e190dd5ef231c6f8da611f8757e55cf850 Author: ModelHub XC Date: Tue Aug 18 03:29:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8f6a25b --- /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 +MT-Merge4-BMU-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-Merge4-BMU-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-Merge4-BMU-gemma-2-9B.IQ4_XS.gguf b/MT-Merge4-BMU-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..1c2692a --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:300abfc0ccd8ff1abe1af224a84845400c00f26a435db310caf8063c43f6103d +size 5223172000 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q2_K.gguf b/MT-Merge4-BMU-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..0655acc --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7545116240cb6cb5080053ad9544efea428a81c1137076369e173600a932265a +size 3805398944 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q3_K_L.gguf b/MT-Merge4-BMU-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..0be23c0 --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa574cea1881111aa90e1ab97fcb3069f64f6bd0caee042245165d1e1701fa06 +size 5132453792 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q3_K_M.gguf b/MT-Merge4-BMU-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..f113f5c --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20a0a9ea7309ee7c9f0db49afe427d2e86f484ad5432862db8e915038812c6d5 +size 4761782176 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q3_K_S.gguf b/MT-Merge4-BMU-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..d41714a --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a8c231b4d34a753117b0d1469ece8e32ad986be50177b3de862e570553cd434 +size 4337665952 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q4_K_M.gguf b/MT-Merge4-BMU-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..e65a26f --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5445d482396b12d452e399fb3a039d62b82959dad0ddd061491c7e802f40ee31 +size 5761058720 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q4_K_S.gguf b/MT-Merge4-BMU-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..cd6d059 --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40075e1ef2fcf3944305a48d8546594363c7f8d350cac35f6f12c499b380898b +size 5478926240 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q5_K_M.gguf b/MT-Merge4-BMU-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..e536c8f --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9be97cc132c05c7361c31e9b2fe4b1cad105b961431f58e4d41a83078685140 +size 6647367584 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q5_K_S.gguf b/MT-Merge4-BMU-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..1bf3f0d --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67fb1c40968de326fcb14d1513916148f404695074fe6ffa463e9c72f86395b7 +size 6483593120 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q6_K.gguf b/MT-Merge4-BMU-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..5edc622 --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6f1bfea732b94e6997ca6a562add08be74bc21b3e927e5c001aa49f8f5d541 +size 7589070752 diff --git a/MT-Merge4-BMU-gemma-2-9B.Q8_0.gguf b/MT-Merge4-BMU-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..1d71994 --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e06f090aa3cfd7bb0e2351189d6181f27ca8c267452e86e34ab61d86c9a14ac1 +size 9827149728 diff --git a/MT-Merge4-BMU-gemma-2-9B.f16.gguf b/MT-Merge4-BMU-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..135ee48 --- /dev/null +++ b/MT-Merge4-BMU-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c3e0d0484a8b569d8bb41ededaf80ba22b8ab9a77d09fffe508d98154319db +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ce80f27 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT-Merge4-BMU-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT-Merge4-BMU-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/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Merge4-BMU-gemma-2-9B-GGUF/resolve/main/MT-Merge4-BMU-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. + +