commit c35e0309dc40745d20ed0db5b8d7eaa291ca0ea5 Author: ModelHub XC Date: Mon Jul 6 05:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT5-MMB-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b99a6bf --- /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 +MT5-MMB-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-MMB-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT5-MMB-gemma-2-9B.IQ4_XS.gguf b/MT5-MMB-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..3ee5983 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c9133309820bda9c17fe0864c074e8c1b29cbbe8c149fffe4735d32ee5c19e0 +size 5223171968 diff --git a/MT5-MMB-gemma-2-9B.Q2_K.gguf b/MT5-MMB-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..26637e5 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e697e7bd4293649bcc35fb98cc1ce3b2d11c0a8f5b052537c18d32db38f29a39 +size 3805398912 diff --git a/MT5-MMB-gemma-2-9B.Q3_K_L.gguf b/MT5-MMB-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..36fcb2c --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de20382949e95f26e775cb9345d07e246c00cd5659509b8c590e425a6b8aebf +size 5132453760 diff --git a/MT5-MMB-gemma-2-9B.Q3_K_M.gguf b/MT5-MMB-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..a1d562f --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0e42983b3ebea95150690bd7e58dc5b0cec5f39b15877d951d241248f9a5c7e +size 4761782144 diff --git a/MT5-MMB-gemma-2-9B.Q3_K_S.gguf b/MT5-MMB-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..f128ff9 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b02577d37fe7930b364a4ebf1564253f08662f872e711796ba0b6824a97ab7 +size 4337665920 diff --git a/MT5-MMB-gemma-2-9B.Q4_K_M.gguf b/MT5-MMB-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..a74af60 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d88b989b6514a8a2d73429044dbfd601176884f36cdd5c3f7d5f79e1cf2576 +size 5761058688 diff --git a/MT5-MMB-gemma-2-9B.Q4_K_S.gguf b/MT5-MMB-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..83a9af5 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74289620856372ebcff789f469891aede1102fd94f84e38ab255a9f4279a8222 +size 5478926208 diff --git a/MT5-MMB-gemma-2-9B.Q5_K_M.gguf b/MT5-MMB-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..6942159 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b05d159f930e734c2af2c6039fed7d73535fbead95a5d6185d218a9df93efc +size 6647367552 diff --git a/MT5-MMB-gemma-2-9B.Q5_K_S.gguf b/MT5-MMB-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..cdcd855 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e23985c76ef0a6735e4d5ebff5c63e12e209bf599f5b2679846c2b16fdc410 +size 6483593088 diff --git a/MT5-MMB-gemma-2-9B.Q6_K.gguf b/MT5-MMB-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..a737736 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1440e270e695d9e439813f088c0593a58ed262bb3e0c1cc44bfdc67a8b8c70dc +size 7589070720 diff --git a/MT5-MMB-gemma-2-9B.Q8_0.gguf b/MT5-MMB-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..c2ea58a --- /dev/null +++ b/MT5-MMB-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bddfb97e254b30c08ab660797aec99ba488b02fc0ad6d98f3be361195705b1c7 +size 9827149696 diff --git a/MT5-MMB-gemma-2-9B.f16.gguf b/MT5-MMB-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..08766f1 --- /dev/null +++ b/MT5-MMB-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d20fd2010659175a9a801e2a538e63c487cfc1a46623ec37ef3b7fe14ac60cef +size 18490681216 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b979282 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT5-MMB-gemma-2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT5-MMB-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/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-MMB-gemma-2-9B-GGUF/resolve/main/MT5-MMB-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. + +