commit 3637d18eb7b5244bff50edd70c21b03c0d94cb29 Author: ModelHub XC Date: Fri Oct 16 10:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3a144b9 --- /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 +MT3-Gen5-MA-gemma-2-MT2E-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.IQ4_XS.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.IQ4_XS.gguf new file mode 100644 index 0000000..9336a29 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de8bf7b3105d286b5bd33702c3ed71ae097215e51bc4814e4a36dd2eef0e76a +size 5223171904 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q2_K.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q2_K.gguf new file mode 100644 index 0000000..0cfc4af --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2945142e63c408ab86fec0ae80f3caf7002e1e8b10ce41f85566b9c56dfd9a06 +size 3805398848 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_L.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_L.gguf new file mode 100644 index 0000000..062281d --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e641d27b99481f76fffe77cba0d4dc2cf4425a977406a3eaee8aa07ef4bda8f +size 5132453696 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_M.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_M.gguf new file mode 100644 index 0000000..695cbcb --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c20338d28c26f26c4bbb004af622205b48cf32831446a0231f8f32c06b18b8b +size 4761782080 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_S.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_S.gguf new file mode 100644 index 0000000..8706dd5 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91f28c9818e058ff875d3b82b8b21dadec1b1a1a4effab60605e7292ed6cdbd +size 4337665856 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_M.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_M.gguf new file mode 100644 index 0000000..1989494 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4229a07049ad7203f47457c15cb72746af3eb4003cb11ef733c2ce882e4ac56 +size 5761058624 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_S.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_S.gguf new file mode 100644 index 0000000..c54c388 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf255d999f836f4b03fe0eaa5bf8f7cd0de72ab4b61b54577ad3be80105a8551 +size 5478926144 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_M.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_M.gguf new file mode 100644 index 0000000..22c0a0f --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c620ea0b5c2d2b0712e9eeb1751cf4963a90d5cfd9781b74e067af4c67e3ea90 +size 6647367488 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_S.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_S.gguf new file mode 100644 index 0000000..a86a6a4 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db4d27e8553c543aaf79dfb033058cd79e7bc4d619e0be0005dd297f43e5d085 +size 6483593024 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q6_K.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q6_K.gguf new file mode 100644 index 0000000..0f90994 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7164c73e2dfa67111e05d19ac5ed872dc443d24f1076f0d9948d631c30be7b +size 7589070656 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.Q8_0.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q8_0.gguf new file mode 100644 index 0000000..278648c --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207665353fc54ebce2de48ee8fd7c448e598eae92d2e0be7147dd9466124489b +size 9827149632 diff --git a/MT3-Gen5-MA-gemma-2-MT2E-9B.f16.gguf b/MT3-Gen5-MA-gemma-2-MT2E-9B.f16.gguf new file mode 100644 index 0000000..128eaa6 --- /dev/null +++ b/MT3-Gen5-MA-gemma-2-MT2E-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e56484e3676cbc43b31ffd801c0412fdeff0cfaf382f453cfa71fdfa1de7332d +size 18490681152 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9b51ba --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen5-MA-gemma-2-MT2E-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen5-MA-gemma-2-MT2E-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/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-MA-gemma-2-MT2E-9B-GGUF/resolve/main/MT3-Gen5-MA-gemma-2-MT2E-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. + +