commit 36169778efd7d2d615c2b093cfbce23037dbd215 Author: ModelHub XC Date: Sun Oct 11 10:45:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemmasutra-9B-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..164d057 --- /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 +Gemmasutra-9B-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemmasutra-9B-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemmasutra-9B-v1.1.IQ4_XS.gguf b/Gemmasutra-9B-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..0bb9a9d --- /dev/null +++ b/Gemmasutra-9B-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e85235d01966fb4e2cae2979e027e6fe8758afc9129157f8313abf85ab1f49b +size 5223171424 diff --git a/Gemmasutra-9B-v1.1.Q2_K.gguf b/Gemmasutra-9B-v1.1.Q2_K.gguf new file mode 100644 index 0000000..8c09200 --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca6405ce5d3c806254475e4bbf80a36b9beba3c1253aa0f51c76586010bf8e2 +size 3805398368 diff --git a/Gemmasutra-9B-v1.1.Q3_K_L.gguf b/Gemmasutra-9B-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..bc166e5 --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c8a2378dabc6939c621263f9d601d14206c492966d0ba6449cb30bfab9bbc3 +size 5132453216 diff --git a/Gemmasutra-9B-v1.1.Q3_K_M.gguf b/Gemmasutra-9B-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..0236b72 --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf6e5ed12abe756a5bf75bdec0a3f99577c3865500a05e3b6b1827bdae0f2f7 +size 4761781600 diff --git a/Gemmasutra-9B-v1.1.Q3_K_S.gguf b/Gemmasutra-9B-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..7313a3d --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adf29806695f10b052d93e72a710fa494af17d069a0abee254b1a8f6432004ab +size 4337665376 diff --git a/Gemmasutra-9B-v1.1.Q4_K_M.gguf b/Gemmasutra-9B-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..6c0ef34 --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7851847dc284accd8a4ddae74747291b1b2b68120c183cdb6f5347ecd5840bbd +size 5761058144 diff --git a/Gemmasutra-9B-v1.1.Q4_K_S.gguf b/Gemmasutra-9B-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..d4b317c --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5b97bddc1c108fe878159d5127415663a7f8875229672dc0e3cbda99179ab2 +size 5478925664 diff --git a/Gemmasutra-9B-v1.1.Q5_K_M.gguf b/Gemmasutra-9B-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..c985d8c --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d532ec606dbaa504373aa4dad1494e5fc5675bd14c7896ef9f312964aa2514 +size 6647367008 diff --git a/Gemmasutra-9B-v1.1.Q5_K_S.gguf b/Gemmasutra-9B-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..a6afb1c --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf6c6303f4f1ba9cf8bd59d5c9e4b7c75c3e75e61af9066f3f7ad3b347174b2 +size 6483592544 diff --git a/Gemmasutra-9B-v1.1.Q6_K.gguf b/Gemmasutra-9B-v1.1.Q6_K.gguf new file mode 100644 index 0000000..c2fbb6b --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e015b3547877ee90871c4ec357f61d949390dc3903092c29653699c75e0f48 +size 7589070176 diff --git a/Gemmasutra-9B-v1.1.Q8_0.gguf b/Gemmasutra-9B-v1.1.Q8_0.gguf new file mode 100644 index 0000000..cf2de90 --- /dev/null +++ b/Gemmasutra-9B-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84464b6b0668ee59b1e8a6b3078013da4cedce759c71fbe003a36834e4f42d20 +size 9827149152 diff --git a/Gemmasutra-9B-v1.1.f16.gguf b/Gemmasutra-9B-v1.1.f16.gguf new file mode 100644 index 0000000..4e671d1 --- /dev/null +++ b/Gemmasutra-9B-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8053dd46471cd6df2125b2abd7382e02fd3a43c82d9d2d8b735e78ebb1c3adac +size 18490680672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..17b64c2 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: TheDrummer/Gemmasutra-9B-v1.1 +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TheDrummer/Gemmasutra-9B-v1.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-i1-GGUF +## 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/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemmasutra-9B-v1.1-GGUF/resolve/main/Gemmasutra-9B-v1.1.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. + +