commit 097e77be8c2d46e97b5f4268bdad16c93980af52 Author: ModelHub XC Date: Wed Oct 7 08:13:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7db5fff --- /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 +Kunoichi-DPO-v2-Instruct-32k-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Kunoichi-DPO-v2-Instruct-32k-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.IQ4_XS.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.IQ4_XS.gguf new file mode 100644 index 0000000..f9495df --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd9dffd863c14cc99bb1fd336389ea2e1b5c06b27e24784ab995ec08aeaf78c +size 3944390048 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q2_K.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q2_K.gguf new file mode 100644 index 0000000..eeb8baf --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe828ff50fa8963f280d872cbf3804728051517cf94871086b8dfdc0e0e66a4 +size 2719243680 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_L.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_L.gguf new file mode 100644 index 0000000..d6442b4 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d8446a9c0f9d352b723d9fd1520b7aa62aa1770e6b8a3eae140ae35caca1cc2 +size 3822026144 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_M.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_M.gguf new file mode 100644 index 0000000..3204dba --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7293c6d2ba4c33d08a7680ee9eb700d823fa9e430e6b735c6bf40662d9c706fd +size 3518987680 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_S.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_S.gguf new file mode 100644 index 0000000..23ae8a3 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d17f03c18b5ecaa5f5bb4b6192a1444245d2d91bd6259e6041bdcc3ce6adfd +size 3164568992 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_M.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_M.gguf new file mode 100644 index 0000000..6f94b72 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f30efba7002dd5ef6c96cb2e897c80fb859dbff2a70f11b77409dff2a17a8d2 +size 4368440736 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_S.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_S.gguf new file mode 100644 index 0000000..4d0b5e5 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33f26abcf4e298e48db11a30a00d460a203b1fcda89fdb35068777015a0ceee +size 4140375456 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_M.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_M.gguf new file mode 100644 index 0000000..1311564 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d9225165c655e20cd833a73ed79471b582b745a7de7b33b28e6ad03f0d8f986 +size 5131410848 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_S.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_S.gguf new file mode 100644 index 0000000..b0f2219 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da4da3633f6d644a21cc17111e446a743bcacd926acce95c290cae97abd23aac +size 4997717408 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q6_K.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q6_K.gguf new file mode 100644 index 0000000..bc0bda4 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5628913cf50e6007ad360973fc124d3fc8d262f51239d2613ca537957c8923d6 +size 5942066592 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.Q8_0.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.Q8_0.gguf new file mode 100644 index 0000000..9435bb0 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05907923e4282c6b70051cbb4bc5f36d31ed8a455c04b6036e8510e29b656694 +size 7695859104 diff --git a/Kunoichi-DPO-v2-Instruct-32k-7B.f16.gguf b/Kunoichi-DPO-v2-Instruct-32k-7B.f16.gguf new file mode 100644 index 0000000..779af32 --- /dev/null +++ b/Kunoichi-DPO-v2-Instruct-32k-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8fbb77c539c042fbff1427f8b8bc8ba58d646ab84b53b154cf78ca6a472b30a +size 14484733344 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f348b35 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mpasila/Kunoichi-DPO-v2-Instruct-32k-7B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/mpasila/Kunoichi-DPO-v2-Instruct-32k-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-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/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-7B.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Kunoichi-DPO-v2-Instruct-32k-7B-GGUF/resolve/main/Kunoichi-DPO-v2-Instruct-32k-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. + +