commit b3ff0883a134ab58b7fecfb94540a80c73174a0f Author: ModelHub XC Date: Mon Jul 6 20:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3556b78 --- /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 +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT2-GP-gemma-2-RIv0.1RAv0.1-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.IQ4_XS.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.IQ4_XS.gguf new file mode 100644 index 0000000..c7b5054 --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c527d23eb63bfffa1c2f5f2b7c353b97cf7b022efaebc7fcba3dc4165a9b9a7 +size 5223172128 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q2_K.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q2_K.gguf new file mode 100644 index 0000000..8657e1a --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96b5521e37308c234d3a54e8df7e48fdc016dc2bddf2edc1a9058780be2731f +size 3805399072 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_L.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_L.gguf new file mode 100644 index 0000000..db3e954 --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe4819e57c5788d6581cfe5b5ca959d81def222957fbea541a80f7f33291ef5 +size 5132453920 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_M.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_M.gguf new file mode 100644 index 0000000..ef8c6bd --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcd00806e8792391702b5f5619cbe877039d7416a05fad2f9e2a5a8fcd59220a +size 4761782304 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_S.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_S.gguf new file mode 100644 index 0000000..a57adbc --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8843e5fcc5c4467ea7b198864c7367af9e40b6ddc68c6689b13c81bd5b3b24fa +size 4337666080 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_M.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_M.gguf new file mode 100644 index 0000000..8b175bb --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a9adcf194ce1f84047cd9710c571c22d59c64f19cd25d7e5a8cda4ec394df1 +size 5761058848 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_S.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_S.gguf new file mode 100644 index 0000000..277606f --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6d250609224cb0eea014aac75d9a520bb4e3a61dca41983bc91429b124c78b +size 5478926368 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_M.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_M.gguf new file mode 100644 index 0000000..4011baf --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a14fee808f8e82a50ebcf0c0b3ce16f1cd686e6712fdf40a956328273b8ef8 +size 6647367712 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_S.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_S.gguf new file mode 100644 index 0000000..d8c1c71 --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71408f22e025dd7558a311cea415b84e5a96f6a1049123b945da3ebbf0b62357 +size 6483593248 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q6_K.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q6_K.gguf new file mode 100644 index 0000000..c685bcc --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1cd15a382ef087d1afc3d4cb1d4d09eb9ccec5402526c779db98cf5a493cf27 +size 7589070880 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q8_0.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q8_0.gguf new file mode 100644 index 0000000..275f566 --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc682ba3f07a2dfbfed28370aa8894ab852cf5f886d8aef44e9a2efee8bd027f +size 9827149856 diff --git a/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.f16.gguf b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.f16.gguf new file mode 100644 index 0000000..92c0c28 --- /dev/null +++ b/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bc55a53529b4583d4617ada0ddb647daa80846197245fca1ecd94945a3e7e72 +size 18490681376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8dae95c --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: zelk12/MT2-GP-gemma-2-RIv0.1RAv0.1-9B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT2-GP-gemma-2-RIv0.1RAv0.1-9B + + +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-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT2-GP-gemma-2-RIv0.1RAv0.1-9B-GGUF/resolve/main/MT2-GP-gemma-2-RIv0.1RAv0.1-9B.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +