commit 74a5d8474a4316c5cfa6e7ddf57be4262f570f6f Author: ModelHub XC Date: Sat Sep 26 11:21:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MT4-Gen5-gemma-2-9B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4a42dc8 --- /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 +MT4-Gen5-gemma-2-9B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.f16.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MT4-Gen5-gemma-2-9B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MT4-Gen5-gemma-2-9B.IQ4_XS.gguf b/MT4-Gen5-gemma-2-9B.IQ4_XS.gguf new file mode 100644 index 0000000..850f1b0 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff21fea7b60c3bc50b9468ec4e4e9bd42f9ebc413948447cd5812a6821164daf +size 5223172000 diff --git a/MT4-Gen5-gemma-2-9B.Q2_K.gguf b/MT4-Gen5-gemma-2-9B.Q2_K.gguf new file mode 100644 index 0000000..6f40f85 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab97d998c550e78e76de1ac8b1d276e424f57a400f601e07079b863094e6610e +size 3805398944 diff --git a/MT4-Gen5-gemma-2-9B.Q3_K_L.gguf b/MT4-Gen5-gemma-2-9B.Q3_K_L.gguf new file mode 100644 index 0000000..b73c065 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1715a7a738f42938dcfda47045fefdc9e43cdd019b21cee20f3e98847392b532 +size 5132453792 diff --git a/MT4-Gen5-gemma-2-9B.Q3_K_M.gguf b/MT4-Gen5-gemma-2-9B.Q3_K_M.gguf new file mode 100644 index 0000000..770cbbf --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be2d89be672c376d514f1cf86990cd56f8ebd1d80c5859fb66d695a70444ef4 +size 4761782176 diff --git a/MT4-Gen5-gemma-2-9B.Q3_K_S.gguf b/MT4-Gen5-gemma-2-9B.Q3_K_S.gguf new file mode 100644 index 0000000..e1f754c --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:707a2d102784bec38f16f59d60a95c12353ecda5a8b781e335d0531262684c6a +size 4337665952 diff --git a/MT4-Gen5-gemma-2-9B.Q4_K_M.gguf b/MT4-Gen5-gemma-2-9B.Q4_K_M.gguf new file mode 100644 index 0000000..bfeffb1 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6682a1201d8e8ef59afcf73fb01985bdb1b66b0d300a789487b3b67236ccde20 +size 5761058720 diff --git a/MT4-Gen5-gemma-2-9B.Q4_K_S.gguf b/MT4-Gen5-gemma-2-9B.Q4_K_S.gguf new file mode 100644 index 0000000..6e1c6ef --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ac141f7bfcdacc89567348156494b19a59654c66af9d0bb800a415c94703ca +size 5478926240 diff --git a/MT4-Gen5-gemma-2-9B.Q5_K_M.gguf b/MT4-Gen5-gemma-2-9B.Q5_K_M.gguf new file mode 100644 index 0000000..8f5279a --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c76c8e15688b07903614d243e789ad9dc4bd9fd9bf792d445c2c0b93b6f486ea +size 6647367584 diff --git a/MT4-Gen5-gemma-2-9B.Q5_K_S.gguf b/MT4-Gen5-gemma-2-9B.Q5_K_S.gguf new file mode 100644 index 0000000..82249d4 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9327198849757732bd6d590ab632cdaa766ba09988e36554303cdaab5a215938 +size 6483593120 diff --git a/MT4-Gen5-gemma-2-9B.Q6_K.gguf b/MT4-Gen5-gemma-2-9B.Q6_K.gguf new file mode 100644 index 0000000..22dc430 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc220b8e344bad5705e2a24aecd937da647c2c068140e4fc9a7b3c0964671d65 +size 7589070752 diff --git a/MT4-Gen5-gemma-2-9B.Q8_0.gguf b/MT4-Gen5-gemma-2-9B.Q8_0.gguf new file mode 100644 index 0000000..c91610d --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5f3151abbf25bc0dbe3730dbae1197d067060dd7fce6c0e8b6bfe3b12a07819 +size 9827149728 diff --git a/MT4-Gen5-gemma-2-9B.f16.gguf b/MT4-Gen5-gemma-2-9B.f16.gguf new file mode 100644 index 0000000..81001f2 --- /dev/null +++ b/MT4-Gen5-gemma-2-9B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcd913bd8ac75bff16353a03c6a0df9a6c76569f23e69d43a2c8d8458c751de8 +size 18490681248 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ae1280 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: zelk12/MT4-Gen5-gemma-2-9B +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/zelk12/MT4-Gen5-gemma-2-9B + + +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/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MT4-Gen5-gemma-2-9B-GGUF/resolve/main/MT4-Gen5-gemma-2-9B.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. + +