commit 1dd94fbd18278f428cf1a27a9060beb6c56e4d3b Author: ModelHub XC Date: Fri Jul 3 02:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a8877ef --- /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-HERMES-MOBIUS-R1-LLAMA.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRAG-HERMES-MOBIUS-R1-LLAMA.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.IQ4_XS.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.IQ4_XS.gguf new file mode 100644 index 0000000..6c1cbb8 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5af87087910531457a087cf0874978169b207aee81805c213b65bddfd60ff0ac +size 4484580800 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q2_K.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q2_K.gguf new file mode 100644 index 0000000..70c2974 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:645ba78e898f25439f651543ae37be8cfc0cb19aa8629e92765665e8170fc3e9 +size 3179316992 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_L.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_L.gguf new file mode 100644 index 0000000..f171745 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f67e051b2b5a463f9112d7a6a676e908b25312c2280b7e093f86a901673e60a4 +size 4322158176 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_M.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_M.gguf new file mode 100644 index 0000000..6c200b1 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c896658bd46a80ef911c129b8be9c158d67bb204f081b2a8563554f658b3e5b1 +size 4019119712 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_S.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_S.gguf new file mode 100644 index 0000000..d3c03e1 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d39700351c14019b5ab00fa49ca0640f137329f9db650d41851e149c40162687 +size 3664701024 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_M.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_M.gguf new file mode 100644 index 0000000..cd6a73b --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a9501897f8d2491b22ceac7a5667f742d8931e15e21b09a38477db26ebdfc9 +size 4920957248 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_S.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_S.gguf new file mode 100644 index 0000000..f666eaf --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17655106a4bdf3cd684dff893562a75b94f26a96788cde30283d98c0c90c5ae1 +size 4692891968 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_M.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_M.gguf new file mode 100644 index 0000000..cb9774d --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec5becbee72cb0431bc9f70bdee276ee5294d19d9e5166fdac7baa20dbbc2912 +size 5733230400 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_S.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_S.gguf new file mode 100644 index 0000000..8ab3ed9 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278c64471926182690004dd4fdc9136a5841b2515e99e9908821852fa0a50b43 +size 5599536960 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q6_K.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q6_K.gguf new file mode 100644 index 0000000..7158475 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cd64461f98c3ebd835addcc3924d347f9977578a38689047adfe0755018328 +size 6596270624 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.Q8_0.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q8_0.gguf new file mode 100644 index 0000000..43658b0 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d499eb66d630db540bdf3bf6be94e1b2e49b8f5dca4fcdde141a62f16f0d9446 +size 8541112416 diff --git a/GRAG-HERMES-MOBIUS-R1-LLAMA.f16.gguf b/GRAG-HERMES-MOBIUS-R1-LLAMA.f16.gguf new file mode 100644 index 0000000..e95c277 --- /dev/null +++ b/GRAG-HERMES-MOBIUS-R1-LLAMA.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e13163830112bd961bbbb290d2a0064fdd742b55f258aa6a87980a546f8ec5d1 +size 16069532256 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fdfa4e7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: avemio-digital/German-RAG-HERMES-MOBIUS-R1-LLAMA +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/avemio-digital/German-RAG-HERMES-MOBIUS-R1-LLAMA + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-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/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRAG-HERMES-MOBIUS-R1-LLAMA-GGUF/resolve/main/GRAG-HERMES-MOBIUS-R1-LLAMA.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. + +