commit 48fa53bd71cb1b6e95233b636c9df462644e26e9 Author: ModelHub XC Date: Mon Jul 6 11:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Spaetzle-v8-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a9506c9 --- /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 +Spaetzle-v8-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Spaetzle-v8-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1afe200 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: cstr/Spaetzle-v8-7b +language: +- de +- en +library_name: transformers +quantized_by: mradermacher +tags: +- merge +- mergekit +- lazymergekit +- flemmingmiguel/NeuDist-Ro-7B +- johannhartmann/Brezn3 +- ResplendentAI/Flora_DPO_7B +--- +## About + + + + + + +static quants of https://huggingface.co/cstr/Spaetzle-v8-7b + + +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/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Spaetzle-v8-7b-GGUF/resolve/main/Spaetzle-v8-7b.f16.gguf) | f16 | 14.6 | 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. + + diff --git a/Spaetzle-v8-7b.IQ4_XS.gguf b/Spaetzle-v8-7b.IQ4_XS.gguf new file mode 100644 index 0000000..6353292 --- /dev/null +++ b/Spaetzle-v8-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebc969142f6294ae83374c24adc24af5430cd57a2798a2a822db975791291fb +size 3944390368 diff --git a/Spaetzle-v8-7b.Q2_K.gguf b/Spaetzle-v8-7b.Q2_K.gguf new file mode 100644 index 0000000..845ca9e --- /dev/null +++ b/Spaetzle-v8-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df7171e49c4da67be0ad445a26a9bf11360da85696a7c451b10ae1e4af546fa +size 2719244000 diff --git a/Spaetzle-v8-7b.Q3_K_L.gguf b/Spaetzle-v8-7b.Q3_K_L.gguf new file mode 100644 index 0000000..c2b1be1 --- /dev/null +++ b/Spaetzle-v8-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449a02e4cb8ffa0eccde1340a44155f02de093659193b625eb91fbd0e4fc5a2a +size 3822026464 diff --git a/Spaetzle-v8-7b.Q3_K_M.gguf b/Spaetzle-v8-7b.Q3_K_M.gguf new file mode 100644 index 0000000..8083df5 --- /dev/null +++ b/Spaetzle-v8-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeca48a841d832a301e95a5815dc5b3f285294fd3359c2fd82d7255383654fae +size 3518988000 diff --git a/Spaetzle-v8-7b.Q3_K_S.gguf b/Spaetzle-v8-7b.Q3_K_S.gguf new file mode 100644 index 0000000..c4f3b07 --- /dev/null +++ b/Spaetzle-v8-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177310a53ba966b5a15b6d98c000f9a398fba72ff7d4fcb337c6dbabcdf6e247 +size 3164569312 diff --git a/Spaetzle-v8-7b.Q4_K_M.gguf b/Spaetzle-v8-7b.Q4_K_M.gguf new file mode 100644 index 0000000..23078d1 --- /dev/null +++ b/Spaetzle-v8-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9849fe4002e39b67cd7a38e3311cbcc4f443e35408c946fc1eac21cf453420 +size 4368441056 diff --git a/Spaetzle-v8-7b.Q4_K_S.gguf b/Spaetzle-v8-7b.Q4_K_S.gguf new file mode 100644 index 0000000..4008b86 --- /dev/null +++ b/Spaetzle-v8-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e475055bebb57871ea3ed20254fb0a229d70c1fb7d59b0d816b50a66375f6722 +size 4140375776 diff --git a/Spaetzle-v8-7b.Q5_K_M.gguf b/Spaetzle-v8-7b.Q5_K_M.gguf new file mode 100644 index 0000000..73aba5e --- /dev/null +++ b/Spaetzle-v8-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8b53f1bcb67fccf639c6d07b159af8beb3f0cc60bf49d019f2d4ea477f0d01a +size 5131411168 diff --git a/Spaetzle-v8-7b.Q5_K_S.gguf b/Spaetzle-v8-7b.Q5_K_S.gguf new file mode 100644 index 0000000..b25afe7 --- /dev/null +++ b/Spaetzle-v8-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b900a73db912ced44b53ff4751e2b5b7df378c0241106a4dc15504abd8820f +size 4997717728 diff --git a/Spaetzle-v8-7b.Q6_K.gguf b/Spaetzle-v8-7b.Q6_K.gguf new file mode 100644 index 0000000..bc499d9 --- /dev/null +++ b/Spaetzle-v8-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f4593bb5093ad4d142af3ebd48ddd71686b5675a54770e223698b15c3ccd56c +size 5942066912 diff --git a/Spaetzle-v8-7b.Q8_0.gguf b/Spaetzle-v8-7b.Q8_0.gguf new file mode 100644 index 0000000..d471c44 --- /dev/null +++ b/Spaetzle-v8-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24d832e5fb2f03509b8897dee6c30411fde0921e7b1178ac5697395652a78967 +size 7695859424 diff --git a/Spaetzle-v8-7b.f16.gguf b/Spaetzle-v8-7b.f16.gguf new file mode 100644 index 0000000..175f2bb --- /dev/null +++ b/Spaetzle-v8-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a80c10fc42e680d5a7a2e032666dd1fea2b2496fcd94647795e19dd67845afe +size 14484733664