commit 04157a945d7c74d45a459723325ed54b1dbcf1d0 Author: ModelHub XC Date: Thu Apr 9 13:34:27 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MN-Sappho-d-12B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3537f56 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +MN-Sappho-d-12B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MN-Sappho-d-12B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MN-Sappho-d-12B.IQ4_XS.gguf b/MN-Sappho-d-12B.IQ4_XS.gguf new file mode 100644 index 0000000..a9cac5e --- /dev/null +++ b/MN-Sappho-d-12B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573367349cb60da7a752f11f6685457d7637eabf3c36a2a75962db5b20790a36 +size 6800054624 diff --git a/MN-Sappho-d-12B.Q2_K.gguf b/MN-Sappho-d-12B.Q2_K.gguf new file mode 100644 index 0000000..7ede4ee --- /dev/null +++ b/MN-Sappho-d-12B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa1c2a269b6ed50543eb69c9aadc1951d739dfcf18852617a07ea90a1f1a496e +size 4791048544 diff --git a/MN-Sappho-d-12B.Q3_K_L.gguf b/MN-Sappho-d-12B.Q3_K_L.gguf new file mode 100644 index 0000000..0b0c0f5 --- /dev/null +++ b/MN-Sappho-d-12B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:161d9b1e136dbdaaba52b3a4b7dc8b6a29033cf198186e5ceb02e6b158475b8b +size 6561503584 diff --git a/MN-Sappho-d-12B.Q3_K_M.gguf b/MN-Sappho-d-12B.Q3_K_M.gguf new file mode 100644 index 0000000..e88bd31 --- /dev/null +++ b/MN-Sappho-d-12B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53da41c7c734479195ffbb9c521d4bbbec1600c477efbe6320b09fc54f403bb0 +size 6083090784 diff --git a/MN-Sappho-d-12B.Q3_K_S.gguf b/MN-Sappho-d-12B.Q3_K_S.gguf new file mode 100644 index 0000000..b2128e5 --- /dev/null +++ b/MN-Sappho-d-12B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbca9079ca91616414f29cab2520d518e0f7dc22290edb8f3f7e01e4004f63db +size 5534226784 diff --git a/MN-Sappho-d-12B.Q4_K_M.gguf b/MN-Sappho-d-12B.Q4_K_M.gguf new file mode 100644 index 0000000..078bf0a --- /dev/null +++ b/MN-Sappho-d-12B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d93c7520d010f9246b85c5fbc5b91286ebc3ceeb47c8c41fb45a5819b5301225 +size 7477205344 diff --git a/MN-Sappho-d-12B.Q4_K_S.gguf b/MN-Sappho-d-12B.Q4_K_S.gguf new file mode 100644 index 0000000..55192a1 --- /dev/null +++ b/MN-Sappho-d-12B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75f2c9dbb6268c6b325043de3323259e15fd2117e4a7d8563510d8af0c3c5a3f +size 7120197984 diff --git a/MN-Sappho-d-12B.Q5_K_M.gguf b/MN-Sappho-d-12B.Q5_K_M.gguf new file mode 100644 index 0000000..0f1073c --- /dev/null +++ b/MN-Sappho-d-12B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a46f44a9519675d74f16996ea67e39f855f93e86104226c35e934302acf2a5a +size 8727632224 diff --git a/MN-Sappho-d-12B.Q5_K_S.gguf b/MN-Sappho-d-12B.Q5_K_S.gguf new file mode 100644 index 0000000..794b174 --- /dev/null +++ b/MN-Sappho-d-12B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a564a0787699b711760238e51e841aca75d920165f6a15aaeb1f80804c906223 +size 8518736224 diff --git a/MN-Sappho-d-12B.Q6_K.gguf b/MN-Sappho-d-12B.Q6_K.gguf new file mode 100644 index 0000000..11b1c1f --- /dev/null +++ b/MN-Sappho-d-12B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16d4e8cd1370b7d95b39f536e6a9f7bd65ed9e3ad892788751a0b848167bda30 +size 10056210784 diff --git a/MN-Sappho-d-12B.Q8_0.gguf b/MN-Sappho-d-12B.Q8_0.gguf new file mode 100644 index 0000000..dd12886 --- /dev/null +++ b/MN-Sappho-d-12B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752810c9046b29f57ce11016116d5b49578cde40945ad69524b7a4d7b1448ad2 +size 13022370144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e335be9 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: mergekit-community/MN-Sappho-d-12B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mergekit-community/MN-Sappho-d-12B + + +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/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q2_K.gguf) | Q2_K | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q3_K_S.gguf) | Q3_K_S | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q3_K_L.gguf) | Q3_K_L | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.IQ4_XS.gguf) | IQ4_XS | 6.9 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q5_K_S.gguf) | Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q5_K_M.gguf) | Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q6_K.gguf) | Q6_K | 10.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MN-Sappho-d-12B-GGUF/resolve/main/MN-Sappho-d-12B.Q8_0.gguf) | Q8_0 | 13.1 | fast, best quality | + +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. + +