commit becc924cce6342f2386452babcc2d8b028d97fef Author: ModelHub XC Date: Tue Jul 7 05:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ad4b3df --- /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-BB-gemma-2-RIv0.1Rv0.3-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT3-BB-gemma-2-RIv0.1Rv0.3-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.IQ4_XS.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.IQ4_XS.gguf new file mode 100644 index 0000000..c06c6df --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad5ed5212cad9081deda441f9e68dc0b6c038fc75e76b01eaddbabd8d991a78 +size 5223172128 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q2_K.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q2_K.gguf new file mode 100644 index 0000000..b39728b --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89366bb2b0405090293d93f8f6e07420d5f4bc4b267ab458519048f018c0e817 +size 3805399072 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_L.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_L.gguf new file mode 100644 index 0000000..78f024d --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ee07a1f9bb8ea17475f93782501423a629ce5f41ce0c4d66b01e399455b771e +size 5132453920 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_M.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_M.gguf new file mode 100644 index 0000000..a27e9a7 --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c358e9a9238fbde053d5f48720d6396a2c60e037d878774364331e0b3b53d5ba +size 4761782304 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_S.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_S.gguf new file mode 100644 index 0000000..9364aaa --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744931342816a68961fd25a66350a8dc13cb1c971e82edc9f9d270155c5acacd +size 4337666080 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_M.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_M.gguf new file mode 100644 index 0000000..bbf12fd --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b87c9c67aa03b7a9f6fd5f12162a698365fe2b2c677b77e44567ea97767085d +size 5761058848 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_S.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_S.gguf new file mode 100644 index 0000000..c257151 --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39efa207611e01991b61db0a623f2fe7ef354e4906d255fbc71bf0525b7e7eb4 +size 5478926368 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_M.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_M.gguf new file mode 100644 index 0000000..06dc928 --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1fc1e74f981a6a58b02902dc1a3517d24798d076dbd23973f6b8eb8bf38ff7 +size 6647367712 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_S.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_S.gguf new file mode 100644 index 0000000..0ff566e --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61e1b2b87a5b6ca922e737d682249b4c3113cb909707a98aae3a18c8b60f731f +size 6483593248 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q6_K.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q6_K.gguf new file mode 100644 index 0000000..2ff2190 --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3b11eff70364a30b86f2970938e86da1714971eb92358787d34772658055bb +size 7589070880 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q8_0.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q8_0.gguf new file mode 100644 index 0000000..1093bb5 --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5801953ab0510feb0cb1ac2e24f3f13e787c1f5974e05d4b79f349221bd48b51 +size 9827149856 diff --git a/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.f16.gguf b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.f16.gguf new file mode 100644 index 0000000..068d0ca --- /dev/null +++ b/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da02d0f003cce32de714cd1ebcc5560c2f178b0507a4c2cf4e69ed90ce706e7c +size 18490681376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..34d77bd --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT3-BB-gemma-2-RIv0.1Rv0.3-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT3-BB-gemma-2-RIv0.1Rv0.3-9B + + +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-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT3-BB-gemma-2-RIv0.1Rv0.3-9B-GGUF/resolve/main/MT3-BB-gemma-2-RIv0.1Rv0.3-9B.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. + +