commit e08ee62316a71922dadce1571995ad5bdc60b2df Author: ModelHub XC Date: Sat Apr 11 04:58:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT5-Gen5-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..09786d7 --- /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-Gen5-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT5-Gen5-gemma-2-9B.IQ4_XS.gguf b/MT5-Gen5-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..0891ba8 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b16c1481845744b751a9d42db10b2457f7800d12fbe2fa35a83e2f7f9a0ba5b +size 5223172000 diff --git a/MT5-Gen5-gemma-2-9B.Q2_K.gguf b/MT5-Gen5-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..21a54b0 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7eb54133e20db7ea3661a7eec08c1b086c94ea8382417faceed839ca5be46ae +size 3805398944 diff --git a/MT5-Gen5-gemma-2-9B.Q3_K_L.gguf b/MT5-Gen5-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..05ee99d --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de2d864597860b5fec3c7b477ccce41fbe7931fbbd4aa873c85fac7ed357f5c +size 5132453792 diff --git a/MT5-Gen5-gemma-2-9B.Q3_K_M.gguf b/MT5-Gen5-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..5d21cad --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:809b036abaa3216953f51cf6dbbf1f1554d56dac28a78ee78a92f23e112f2887 +size 4761782176 diff --git a/MT5-Gen5-gemma-2-9B.Q3_K_S.gguf b/MT5-Gen5-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..b862081 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fb243fb4af18eb0cf77727bdebde779db214b0b555da488d7d11ef170b527fb +size 4337665952 diff --git a/MT5-Gen5-gemma-2-9B.Q4_K_M.gguf b/MT5-Gen5-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..46e8d79 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bef5530a3883dc7369e380cf25730e6a51ab7e105b6c17f4f2e55ca328010fa6 +size 5761058720 diff --git a/MT5-Gen5-gemma-2-9B.Q4_K_S.gguf b/MT5-Gen5-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..abfb0ad --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ccad0b0239c9b177c7c8ba5fe6ee6cd661e67671df5302d50dd1cfd98f018ce +size 5478926240 diff --git a/MT5-Gen5-gemma-2-9B.Q5_K_M.gguf b/MT5-Gen5-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..ef283cb --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8117bb61ab62eed556ec54b2606f52c805c6e8c53117898862f02c676c4ab6be +size 6647367584 diff --git a/MT5-Gen5-gemma-2-9B.Q5_K_S.gguf b/MT5-Gen5-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..ff2934c --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd3e413637b32d7a1833ea08b9f6d1d147181e91df9195201bf1703c4ff258a5 +size 6483593120 diff --git a/MT5-Gen5-gemma-2-9B.Q6_K.gguf b/MT5-Gen5-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..cb38851 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b83384a3448470e981b89dc383ef212e496d1ec97245099ecefff0587591f9 +size 7589070752 diff --git a/MT5-Gen5-gemma-2-9B.Q8_0.gguf b/MT5-Gen5-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..7af54c6 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d2f83e68d4c2d9b6005e01be7045f41d7a019bb55c928acb4adb75b673ae58d +size 9827149728 diff --git a/MT5-Gen5-gemma-2-9B.f16.gguf b/MT5-Gen5-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..af043a5 --- /dev/null +++ b/MT5-Gen5-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cacd4273bd48d50b123307eb7e1caa30f2d13636f85dbcb1bcd1c216ab43f3b +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fcb3681 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: zelk12/MT5-Gen5-gemma-2-9B +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT5-Gen5-gemma-2-9B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT5-Gen5-gemma-2-9B-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/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-gemma-2-9B-GGUF/resolve/main/MT5-Gen5-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. + +