commit 3bd8656bc8831b6f9c50dc0850305f897cb26b06 Author: ModelHub XC Date: Fri Apr 10 18:14:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-German-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5022c16 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +Llama3-German-8B.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-German-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-German-8B.IQ3_M.gguf b/Llama3-German-8B.IQ3_M.gguf new file mode 100644 index 0000000..eae580e --- /dev/null +++ b/Llama3-German-8B.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b82ac8e36f146ccb848a8acee15870daaa207cb2b6207fc558276d42cb6b549 +size 3784823328 diff --git a/Llama3-German-8B.IQ3_S.gguf b/Llama3-German-8B.IQ3_S.gguf new file mode 100644 index 0000000..dd46d79 --- /dev/null +++ b/Llama3-German-8B.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a712c22685cc5071cf2607f0ae9b884a06b6b65eeaf06a6583e030d60614334 +size 3682325024 diff --git a/Llama3-German-8B.IQ3_XS.gguf b/Llama3-German-8B.IQ3_XS.gguf new file mode 100644 index 0000000..155b1fd --- /dev/null +++ b/Llama3-German-8B.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aadc92f2d2aaf2409ba238c0bd99ba93daefcb125360ec0f4b188966486a3a3 +size 3518747168 diff --git a/Llama3-German-8B.IQ4_XS.gguf b/Llama3-German-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ba1e800 --- /dev/null +++ b/Llama3-German-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:503d2bfc7e846277bc5bb269c8326ad6c6f6cf0c33cff6f7f7e218b54f694712 +size 4484362784 diff --git a/Llama3-German-8B.Q2_K.gguf b/Llama3-German-8B.Q2_K.gguf new file mode 100644 index 0000000..26fdb55 --- /dev/null +++ b/Llama3-German-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd01d68b62d08af9892c68eb0b37eb892de45dfc158917dd91cd45d457652ca +size 3179131424 diff --git a/Llama3-German-8B.Q3_K_L.gguf b/Llama3-German-8B.Q3_K_L.gguf new file mode 100644 index 0000000..cdc52e8 --- /dev/null +++ b/Llama3-German-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21de88c837272a3a605bf891b004107affc4ed61d6780c625d68fa4777288668 +size 4321956384 diff --git a/Llama3-German-8B.Q3_K_M.gguf b/Llama3-German-8B.Q3_K_M.gguf new file mode 100644 index 0000000..cf4a952 --- /dev/null +++ b/Llama3-German-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31da9161d7711b2a2f0bae8cb8517000e3ac49816ba379b5453be8ea84b884c9 +size 4018917920 diff --git a/Llama3-German-8B.Q3_K_S.gguf b/Llama3-German-8B.Q3_K_S.gguf new file mode 100644 index 0000000..03c363e --- /dev/null +++ b/Llama3-German-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:421dd9f7c13d20ffc194c18d2c03071471f3daf607e599ebd271bc9690043e92 +size 3664499232 diff --git a/Llama3-German-8B.Q4_K_M.gguf b/Llama3-German-8B.Q4_K_M.gguf new file mode 100644 index 0000000..fcb7794 --- /dev/null +++ b/Llama3-German-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ab0372fea29061c37e1f71baeb139ca2dce8b346866b34b09605a8e9c705f3 +size 4920734240 diff --git a/Llama3-German-8B.Q4_K_S.gguf b/Llama3-German-8B.Q4_K_S.gguf new file mode 100644 index 0000000..54ed25e --- /dev/null +++ b/Llama3-German-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca0605f5c001d27031ddc3cc178eb02d093b71ace97bbf8ca908514e6fbba652 +size 4692668960 diff --git a/Llama3-German-8B.Q5_K_M.gguf b/Llama3-German-8B.Q5_K_M.gguf new file mode 100644 index 0000000..129e470 --- /dev/null +++ b/Llama3-German-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f844075213d5b68d34bc9b17691a428255e03ce92a4995ea25ad57cb2f81687e +size 5732987424 diff --git a/Llama3-German-8B.Q5_K_S.gguf b/Llama3-German-8B.Q5_K_S.gguf new file mode 100644 index 0000000..770119b --- /dev/null +++ b/Llama3-German-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a3769432b356d38c1466517b7743d2c77d8e9b3c931d1f5b25ff4019582050a +size 5599293984 diff --git a/Llama3-German-8B.Q6_K.gguf b/Llama3-German-8B.Q6_K.gguf new file mode 100644 index 0000000..b0107bb --- /dev/null +++ b/Llama3-German-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67359b056ae81987e41ad39c057c8bd1975c9a5363edb41532387462a19ebf6b +size 6596006432 diff --git a/Llama3-German-8B.Q8_0.gguf b/Llama3-German-8B.Q8_0.gguf new file mode 100644 index 0000000..2ffd34e --- /dev/null +++ b/Llama3-German-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e509bd9a9c7f52a58a9f45a19ab03a0ca6bf05e29b6025848b7626764a8c557 +size 8540770848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7f2411d --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: DiscoResearch/Llama3-German-8B +language: +- de +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/DiscoResearch/Llama3-German-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-German-8B-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/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-German-8B-GGUF/resolve/main/Llama3-German-8B.Q8_0.gguf) | Q8_0 | 8.6 | 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. + +