commit 4e856b7fac4270bc1a6454bc2df27c39c82e04fc Author: ModelHub XC Date: Wed May 6 01:16:04 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3f54921 --- /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 +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.IQ4_XS.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.IQ4_XS.gguf new file mode 100644 index 0000000..4fec6bb --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d45996457924ce8d3ec729fc1e4b5953acd192d7927e07f5ed91f9c744590ad +size 4484366560 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q2_K.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q2_K.gguf new file mode 100644 index 0000000..9bbcdee --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77f372a0ce871c2ad093a00bc12e8dfa724dbaed3fde7eac7bb4c0d49eb83bc +size 3179135200 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_L.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_L.gguf new file mode 100644 index 0000000..4c4bb43 --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:902c39ca55bddcc54b665267c7cbc6ba4ce99dbb68f2e59920c59bdd04b1e96f +size 4321960160 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_M.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_M.gguf new file mode 100644 index 0000000..78b618e --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a6f79194d1f45a2d0b01b143c2040faf38dc9cccef124b348ef8763320d15f +size 4018921696 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_S.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_S.gguf new file mode 100644 index 0000000..8663a35 --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78ead60a360e5eae72b6bb1bf8aa39ebbea005424f949be5667edcb49f391ee5 +size 3664503008 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_M.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_M.gguf new file mode 100644 index 0000000..3ad0b46 --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c478f68cef3e8ef86ceb0ae8f937780319b5112f90116d492b116be5da61e7ca +size 4920738016 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_S.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_S.gguf new file mode 100644 index 0000000..73d6181 --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed4494657d2a3d6d3daf3f0172f5a190fdc46012211f143e7e63732e0a81ae0 +size 4692672736 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_M.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_M.gguf new file mode 100644 index 0000000..d85117d --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5be7d90b858f2360a949c5f9353901c97793c9b49648a32bfbaf85d32f172e42 +size 5732991200 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_S.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_S.gguf new file mode 100644 index 0000000..05ee8ba --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67aac6c212458fa15609d73134baef3c7ea2bd1223256deb3f26351beab0e0bc +size 5599297760 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q6_K.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q6_K.gguf new file mode 100644 index 0000000..c34e75d --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd5e6b2fd3872effe98b02cc8ce3d12b9b3f92446d2b930ba9860babea6f6ae1 +size 6596010208 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q8_0.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q8_0.gguf new file mode 100644 index 0000000..569d8c9 --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aeacb414ec15765e1201fdda983719ca5beb907fd15e1381b85aca83a2973a2 +size 8540774624 diff --git a/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.f16.gguf b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.f16.gguf new file mode 100644 index 0000000..6575b9f --- /dev/null +++ b/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6cb7507e796c4e26caa729032ef47f72352532fa8c96a5e6df2c67ce7009cd +size 16068894944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..745e7d2 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: avemio-digital/German-RAG-MOBIUS-R1-LLAMA-DISTILL-MERGE +datasets: +- avemio/German-RAG-HARD-REASONING-DE-THINKING +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/avemio-digital/German-RAG-MOBIUS-R1-LLAMA-DISTILL-MERGE + + +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/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE-GGUF/resolve/main/GRAG-MOBIUS-R1-LLAMA-DISTILL-MERGE.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +