commit 2a9f6da3a9922485fc593fd438f01cf4f7a097be Author: ModelHub XC Date: Sat Aug 15 22:51:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ebbeab2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +Llama-Guard-2-8B-German-v0.2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-Guard-2-8B-German-v0.2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-Guard-2-8B-German-v0.2.IQ3_M.gguf b/Llama-Guard-2-8B-German-v0.2.IQ3_M.gguf new file mode 100644 index 0000000..0763878 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41f1052b9deb2f27a95cd471ad4731c5d274ef3c326dc06fdde61a9731740829 +size 3784824416 diff --git a/Llama-Guard-2-8B-German-v0.2.IQ3_S.gguf b/Llama-Guard-2-8B-German-v0.2.IQ3_S.gguf new file mode 100644 index 0000000..c514bf1 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7d4d233481f87d41492251c11bc7ea90c5af75fe01383ebc844e7faa351485 +size 3682326112 diff --git a/Llama-Guard-2-8B-German-v0.2.IQ3_XS.gguf b/Llama-Guard-2-8B-German-v0.2.IQ3_XS.gguf new file mode 100644 index 0000000..fe76016 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac72d4f4ed27c9bed47842b6b82b019efcc40e36292113a67745622ac81f703 +size 3518748256 diff --git a/Llama-Guard-2-8B-German-v0.2.IQ4_XS.gguf b/Llama-Guard-2-8B-German-v0.2.IQ4_XS.gguf new file mode 100644 index 0000000..cda97b3 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d4c8de78ade88587ebabbd944c1313e4e1d405113b2bfacd2d77c075e44bef7 +size 4484363872 diff --git a/Llama-Guard-2-8B-German-v0.2.Q2_K.gguf b/Llama-Guard-2-8B-German-v0.2.Q2_K.gguf new file mode 100644 index 0000000..58b2df5 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e16d4760ed2290d34990666cfc8df542366cf5d6fe3e4e14fef50e6c207c209 +size 3179132512 diff --git a/Llama-Guard-2-8B-German-v0.2.Q3_K_L.gguf b/Llama-Guard-2-8B-German-v0.2.Q3_K_L.gguf new file mode 100644 index 0000000..5c346a1 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126052b4e23b99e9ca7d4298e532245fad076a2777222e03d7c8397f94941c99 +size 4321957472 diff --git a/Llama-Guard-2-8B-German-v0.2.Q3_K_M.gguf b/Llama-Guard-2-8B-German-v0.2.Q3_K_M.gguf new file mode 100644 index 0000000..1629557 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93940ebdf096ebe6d0957f81a2c96e5e2431e68dc3352ea0e59d3944895fb5fc +size 4018919008 diff --git a/Llama-Guard-2-8B-German-v0.2.Q3_K_S.gguf b/Llama-Guard-2-8B-German-v0.2.Q3_K_S.gguf new file mode 100644 index 0000000..511b1a8 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d4c3180b550a910d8bf6448d149ea08c4c0531cb0080d18a4813cd3f396ac1 +size 3664500320 diff --git a/Llama-Guard-2-8B-German-v0.2.Q4_K_M.gguf b/Llama-Guard-2-8B-German-v0.2.Q4_K_M.gguf new file mode 100644 index 0000000..738f0b6 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e370f6260299c2e47a02fe0c92d692952477a509ea9cb0ecf18114c77c2962a +size 4920735328 diff --git a/Llama-Guard-2-8B-German-v0.2.Q4_K_S.gguf b/Llama-Guard-2-8B-German-v0.2.Q4_K_S.gguf new file mode 100644 index 0000000..c60d1a2 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:585e03ecad27a4123c0074d043aba58e766e23859fc5cb8ba38a6e0381fdaffb +size 4692670048 diff --git a/Llama-Guard-2-8B-German-v0.2.Q5_K_M.gguf b/Llama-Guard-2-8B-German-v0.2.Q5_K_M.gguf new file mode 100644 index 0000000..91b7001 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d45a63d4f08eece77343cc53499aa2e150c3b4e9ac446190b17527c9d099d8e +size 5732988512 diff --git a/Llama-Guard-2-8B-German-v0.2.Q5_K_S.gguf b/Llama-Guard-2-8B-German-v0.2.Q5_K_S.gguf new file mode 100644 index 0000000..02ddc25 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee6b5e71d00d398d762f8b4d6184e71a6f9cddba26ae79ec381b504584c800b +size 5599295072 diff --git a/Llama-Guard-2-8B-German-v0.2.Q6_K.gguf b/Llama-Guard-2-8B-German-v0.2.Q6_K.gguf new file mode 100644 index 0000000..dc466e3 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7574cf83f9917cc4a9bb80a62ad85d1b62e452da554897be39eb692b3300149a +size 6596007520 diff --git a/Llama-Guard-2-8B-German-v0.2.Q8_0.gguf b/Llama-Guard-2-8B-German-v0.2.Q8_0.gguf new file mode 100644 index 0000000..26b987e --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00808868b6cdfde0c0c828eb862d6d1179f65f3ed4ae8022fc3ed942718ebdf4 +size 8540771936 diff --git a/Llama-Guard-2-8B-German-v0.2.f16.gguf b/Llama-Guard-2-8B-German-v0.2.f16.gguf new file mode 100644 index 0000000..e3078e3 --- /dev/null +++ b/Llama-Guard-2-8B-German-v0.2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:796237021d24add62796c42db7c6b4c69bceb3ab72548a1ffda7db21abbd41cd +size 16068892256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0b70c1f --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: felfri/Llama-Guard-2-8B-German-v0.2 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/felfri/Llama-Guard-2-8B-German-v0.2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-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/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-Guard-2-8B-German-v0.2-GGUF/resolve/main/Llama-Guard-2-8B-German-v0.2.f16.gguf) | f16 | 16.2 | 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. + +