commit 12934d63ce6797e25da368c8f45583af25b51b17 Author: ModelHub XC Date: Fri Oct 2 18:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3448bbd --- /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-MA-gemma-2-MTg2MT2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT5-Gen5-MA-gemma-2-MTg2MT2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.IQ4_XS.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..f62999c --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db6915bacfcbfda17f70e949f4cd5c53f02732e1ae30b30294faff38ac8dff3d +size 5223171904 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q2_K.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q2_K.gguf new file mode 100644 index 0000000..4485883 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb8062a6ce641b19b0e7ed90139265955ecdeef3a7bba0bb96f0becdf4e227d1 +size 3805398848 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_L.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..df9151b --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76ec7a90abb97da70919ceb8c87387622e4c327cfb64eb6c77c31943cd34c9a9 +size 5132453696 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_M.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..bfd366a --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242e3eb854a92f5870a4fadab5f14675885c64fcc30eeb50d5b1d18e04a07cf9 +size 4761782080 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_S.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..b1bda23 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3be1f43119a42677bca919dbffd13f6b92ba75d0aab9866bf8856e08d8f0f53e +size 4337665856 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_M.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..982339a --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:489955d31163f0797bfad81f07165e076c27dc49e4f19183dfd803d723758df6 +size 5761058624 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_S.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..68dde89 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a10b7520de5397f396fde4be71c40b1805a47b53f1ce57ef8f03d984c5b059 +size 5478926144 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_M.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..af76e88 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5755fe777860993ab31eca523f0bb25fef6e64172f2927e4d15536b7699f9ae9 +size 6647367488 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_S.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..7b15b9e --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cab69967fb527836093ab180b4d6eff4709617bdb24f49bd2c7fae4753fb984 +size 6483593024 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q6_K.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q6_K.gguf new file mode 100644 index 0000000..6473666 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c238c06c69f125c3512311e3bf36c949fe146aec77c1704661f9b90c6cfa80af +size 7589070656 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q8_0.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q8_0.gguf new file mode 100644 index 0000000..40fa771 --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41d47bdd76d4351dcea534bb18277a44e23b87d2ce49e1f315bd72f3e10dae2 +size 9827149632 diff --git a/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.f16.gguf b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.f16.gguf new file mode 100644 index 0000000..075687a --- /dev/null +++ b/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b3ad460f049d3ccfcd7d4d2507b168772f639522a60ce47fac6c72853ac7f2 +size 18490681152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..269307a --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: zelk12/MT5-Gen5-MA-gemma-2-MTg2MT2-9B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT5-Gen5-MA-gemma-2-MTg2MT2-9B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MT5-Gen5-MA-gemma-2-MTg2MT2-9B-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-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT5-Gen5-MA-gemma-2-MTg2MT2-9B-GGUF/resolve/main/MT5-Gen5-MA-gemma-2-MTg2MT2-9B.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. + +