commit a940f14b2f7f560fdd52e7d4decd3fc0bce0d74d Author: ModelHub XC Date: Tue Oct 20 14:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b67604a --- /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-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.IQ4_XS.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.IQ4_XS.gguf new file mode 100644 index 0000000..1834292 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f28cf9f1eae1314d17bc36436ba97e70073007f229dd70c7b702e4bab0d32d +size 5223172096 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q2_K.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q2_K.gguf new file mode 100644 index 0000000..42e298e --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac327a299a7397b1fc61219ad3bbc6974086a816fbcb71ccbe631756d17ac7fc +size 3805399040 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_L.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_L.gguf new file mode 100644 index 0000000..be5e061 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ac58737c583b39c793a371dccef9e4249df4b1a3255b7ee8789c34739e58a7 +size 5132453888 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_M.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_M.gguf new file mode 100644 index 0000000..a61a339 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1691fbdc380e15075efe1ba50100b24fe5df9535ef46d42d5b17dd04309cd6aa +size 4761782272 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_S.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_S.gguf new file mode 100644 index 0000000..35e56b3 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af4f34b5ef5e8ceb5690a06696ad9f8ddd962ae36e0321903a22988c6fcc1371 +size 4337666048 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_M.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_M.gguf new file mode 100644 index 0000000..d4c5014 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5084731531652e8cda189e1d559e870068b55e2e95fd51e9f53e9acea88b9535 +size 5761058816 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_S.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_S.gguf new file mode 100644 index 0000000..c697740 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513186b41ff5727aaae016fe4ce67143f20457a2aa68028ba8546acce07ce079 +size 5478926336 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_M.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_M.gguf new file mode 100644 index 0000000..23fac88 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8143fc60a8179d52e7c2511a1388810de9d7b2cfe5c9e8c64695f296b2bb0cb1 +size 6647367680 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_S.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_S.gguf new file mode 100644 index 0000000..35d17c7 --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:601efcc10fadcb6a258510f7fdeebc4d55711b69d35d3e43c47d2640047e180d +size 6483593216 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q6_K.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q6_K.gguf new file mode 100644 index 0000000..608035f --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96302e3763530153172a14885fbdfab43e57856fb5bd1d9f9886c69dbcf22367 +size 7589070848 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q8_0.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q8_0.gguf new file mode 100644 index 0000000..0a0af6a --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cdb6b3e0ba0f4cb4b9a59bc8655587aece6dd4646ef34c36a76eddaf873086 +size 9827149824 diff --git a/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.f16.gguf b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.f16.gguf new file mode 100644 index 0000000..2554f2b --- /dev/null +++ b/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc915fdf40f0a6daf7daa0cd7027e04163960cadb3a2e1573193ec723a343d15 +size 18490681344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..14a1cb4 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1 + + +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-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1-GGUF/resolve/main/MT3-Gen5-BB-gemma-2-RAv0.1MT2-9B_v1.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. + +