commit 899a3ec6b025a3c9ec01cd831caaf8a67245390d Author: ModelHub XC Date: Sun Oct 11 02:40:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nereus-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..62b66fa --- /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 +Nereus-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nereus-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nereus-7B.IQ4_XS.gguf b/Nereus-7B.IQ4_XS.gguf new file mode 100644 index 0000000..be1e9b7 --- /dev/null +++ b/Nereus-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098ae5e4c4c1af1c57ead2c1b253124d76153e14a6b71606c08da889e6bd2316 +size 3944401184 diff --git a/Nereus-7B.Q2_K.gguf b/Nereus-7B.Q2_K.gguf new file mode 100644 index 0000000..ef1f3db --- /dev/null +++ b/Nereus-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:229024ff0b7419c2f4b5f513882b838d69fcf7fce2590c26f47f65405384b8d2 +size 2719253152 diff --git a/Nereus-7B.Q3_K_L.gguf b/Nereus-7B.Q3_K_L.gguf new file mode 100644 index 0000000..b0be9b8 --- /dev/null +++ b/Nereus-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a551b33efd41f3d326d8e2fdb00ff7cb8d1a0447cc6270bd9318cc9e37cce34d +size 3822036448 diff --git a/Nereus-7B.Q3_K_M.gguf b/Nereus-7B.Q3_K_M.gguf new file mode 100644 index 0000000..5676317 --- /dev/null +++ b/Nereus-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99eed9c5c5a156cc969e6f3f4f6aa32e03151eb5dac1694afdb4a0b39c606379 +size 3518997984 diff --git a/Nereus-7B.Q3_K_S.gguf b/Nereus-7B.Q3_K_S.gguf new file mode 100644 index 0000000..555e4a7 --- /dev/null +++ b/Nereus-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4164402e6a37e6a22b7bbb0776fba217bbf32de5a845c017e36620845f8adfe7 +size 3164579296 diff --git a/Nereus-7B.Q4_K_M.gguf b/Nereus-7B.Q4_K_M.gguf new file mode 100644 index 0000000..9fa905c --- /dev/null +++ b/Nereus-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5763e819e5cb226a9801986fb03f74cf6d131a335666089d732b0d7aa5bde21 +size 4368452128 diff --git a/Nereus-7B.Q4_K_S.gguf b/Nereus-7B.Q4_K_S.gguf new file mode 100644 index 0000000..348727a --- /dev/null +++ b/Nereus-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:795b4a7cad0fb46cafb05e0dbd55a254526471344cab7002ea13b0c3c5f57858 +size 4140386848 diff --git a/Nereus-7B.Q5_K_M.gguf b/Nereus-7B.Q5_K_M.gguf new file mode 100644 index 0000000..bca752b --- /dev/null +++ b/Nereus-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10ed4479043f8cffd329dbeea35ca4066491af0e431316d27c0665496ede8764 +size 5131423264 diff --git a/Nereus-7B.Q5_K_S.gguf b/Nereus-7B.Q5_K_S.gguf new file mode 100644 index 0000000..e1d857c --- /dev/null +++ b/Nereus-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc839dfbd12e13d83512af1891306c4da5d1b9137da527c0a634ba81a16e665 +size 4997729824 diff --git a/Nereus-7B.Q6_K.gguf b/Nereus-7B.Q6_K.gguf new file mode 100644 index 0000000..3cdf90c --- /dev/null +++ b/Nereus-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:438ea11b690315e48bb58e633a3985a5ee9de5cf7c7b6c96afa79644b04c68d9 +size 5942080096 diff --git a/Nereus-7B.Q8_0.gguf b/Nereus-7B.Q8_0.gguf new file mode 100644 index 0000000..a030194 --- /dev/null +++ b/Nereus-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3476b7ef088d7cccea7ebece68c2614bddae6d8a62b82a43b72a7300d5b7112 +size 7695876576 diff --git a/Nereus-7B.f16.gguf b/Nereus-7B.f16.gguf new file mode 100644 index 0000000..69f917b --- /dev/null +++ b/Nereus-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57bcf1500c8d377056608a1190e1766969aef2412d930d7be0d4899c9d715bf9 +size 14484766176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b561805 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: saucam/Nereus-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- merge +- mergekit +- cognitivecomputations/dolphin-2.8-mistral-7b-v02 +- NousResearch/Hermes-2-Pro-Mistral-7B +--- +## About + + + + + + +static quants of https://huggingface.co/saucam/Nereus-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nereus-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nereus-7B-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/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nereus-7B-GGUF/resolve/main/Nereus-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. + +