commit 129d3f8aa7989d37d264333680af1cf00c6248a8 Author: ModelHub XC Date: Sat Sep 12 08:34:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35cfe2c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.IQ4_XS.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.IQ4_XS.gguf new file mode 100644 index 0000000..78842a9 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e005e8cd4d3d14638531dfcf376383d1ecbd33c6c1d259639b16b1910dd8302 +size 5223171936 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q2_K.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q2_K.gguf new file mode 100644 index 0000000..d832791 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26be27da1d321fd9b88315144f434718f26857fb2888a0853cd978a97ed67b0f +size 3805398880 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_L.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_L.gguf new file mode 100644 index 0000000..52b52b7 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103c11663c4090abafb190b35651667ed5db36736c18c0f99a84e021118ab45c +size 5132453728 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_M.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_M.gguf new file mode 100644 index 0000000..15757a3 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2175866a2bf6f3633eccaf5c149af8666000535581c8563e1fdaae42201ef0 +size 4761782112 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_S.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_S.gguf new file mode 100644 index 0000000..69fe89d --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241f666e2ee6a249d0fb615c9f7e83a46bc7fcfec85871eddaf83c0fef903159 +size 4337665888 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_0_4_4.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_0_4_4.gguf new file mode 100644 index 0000000..54be079 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d29a58d99edd6b7fa72a63a08dc66d0e2d01ea7c94a699b9ae67b1a538ef19 +size 5443143520 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_M.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_M.gguf new file mode 100644 index 0000000..49cf320 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ba5718cd3856168d7cd78d3ddca94ca9378e68b1e54b13234766b6630cd5210 +size 5761058656 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_S.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_S.gguf new file mode 100644 index 0000000..2974a76 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99530b3763cfcbd5de270ecd710b51aa6d970651b0c0f519ac93ee3df1f6e1b6 +size 5478926176 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_M.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_M.gguf new file mode 100644 index 0000000..7d276d5 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9881ca89105e6c139e27478b7641109cc7c05964c53fa76f7bc0a9fa780de0df +size 6647367520 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_S.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_S.gguf new file mode 100644 index 0000000..70c9dc0 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89a88b963561a255c5be8861b22f04cec0b2ba3ba941e30b9d970ac5022028e +size 6483593056 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q6_K.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q6_K.gguf new file mode 100644 index 0000000..48fc496 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d7779a0277235491ced5c254bb53301ccbbb50e15a90e3a5e0976d75fa4930 +size 7589070688 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q8_0.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q8_0.gguf new file mode 100644 index 0000000..498f5f1 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4386e2638c3ec59212a4e487d7ed607216fb633e02ada027617c7fade84c27d +size 9827149664 diff --git a/MT-Gen3-MA-gemma-2-S5MT4g1-9B.f16.gguf b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.f16.gguf new file mode 100644 index 0000000..4f7adf2 --- /dev/null +++ b/MT-Gen3-MA-gemma-2-S5MT4g1-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dab9597e7020b14ccbf73311d659f313a3d65a97dec6aef38e6d380f524b4948 +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..85fb994 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: zelk12/MT-Gen3-MA-gemma-2-S5MT4g1-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT-Gen3-MA-gemma-2-S5MT4g1-9B + + +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-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT-Gen3-MA-gemma-2-S5MT4g1-9B-GGUF/resolve/main/MT-Gen3-MA-gemma-2-S5MT4g1-9B.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. + +