commit 8508b1ad14f272a3299c8050c79f144941934b18 Author: ModelHub XC Date: Sun Jul 5 15:32:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3f033f --- /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 +MT2-Gen3-BB-gemma-2-MTMS2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.IQ4_XS.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..b26a09d --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1454a798dd3ec68629a39412b1a0de2c7830c5f78cea33a51e17033ac0f3b392 +size 5223171936 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q2_K.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q2_K.gguf new file mode 100644 index 0000000..6f88e4a --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c68f2ebf65b16274ee640e849c6a4d8c2f5bf8ccba044daf69e2a9df9f3b202 +size 3805398880 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_L.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..c857a19 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0679b89553c59cb9e677a69d3377600da0dcbd87b0505f04c3e72395e7e98c8f +size 5132453728 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_M.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..32b9eb6 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59bb6ac1e3967ba76d611ee39bacd8a2c71c0ad056f0241e3ff44ba38b988c0b +size 4761782112 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_S.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..b5152d8 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2547009d98adc5257aed4bc8b2426920f903a0ebb3e8c3a3a6f0ebaa7795f3c +size 4337665888 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_0_4_4.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_0_4_4.gguf new file mode 100644 index 0000000..e2845dc --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa04f2324518d730ef5688a9c74c1c1289754f402a277a5238d1207c8d5b0f57 +size 5443143520 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_M.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..5182c14 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88fe69fdb9a1d7c9ccca9d033e18cb101fc1e756744821e2943da7dd5f5a4a72 +size 5761058656 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_S.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..f37298f --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e9982365fa1bd8931eb2c1a1dc627bce646b1e6de2364cad58eb53bd42eaf9 +size 5478926176 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_M.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..12aa567 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f2e6b172077a0c2a16c1643c57385af032faed3a522afb627a69afd5a0160d5 +size 6647367520 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_S.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..bd8b685 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6310ce32393c66d4caefeeb8ff8cc2fe4cdb7f0f81fc58293b1c092f05d0cf93 +size 6483593056 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q6_K.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q6_K.gguf new file mode 100644 index 0000000..a98428b --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1522812822a1a4c394e9c2759491963381e805d3bc4c970e3c3a6857578af87e +size 7589070688 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q8_0.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q8_0.gguf new file mode 100644 index 0000000..36a0969 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e64967cc04e086f94650edc5ebedd493f75ad0abae5fd83f6ecf5a465571e5 +size 9827149664 diff --git a/MT2-Gen3-BB-gemma-2-MTMS2-9B.f16.gguf b/MT2-Gen3-BB-gemma-2-MTMS2-9B.f16.gguf new file mode 100644 index 0000000..4365993 --- /dev/null +++ b/MT2-Gen3-BB-gemma-2-MTMS2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f71702613a7705aa21a48528e998faec7c929fe4ef3316ec5307c08c535a9d +size 18490681184 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4bb2425 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: zelk12/MT2-Gen3-BB-gemma-2-MTMS2-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT2-Gen3-BB-gemma-2-MTMS2-9B + + +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/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_0_4_4.gguf) | Q4_0_4_4 | 5.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-Gen3-BB-gemma-2-MTMS2-9B-GGUF/resolve/main/MT2-Gen3-BB-gemma-2-MTMS2-9B.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. + +