commit 3c5f5a66ca7ba027c90e2c3abf146c35acf8eb70 Author: ModelHub XC Date: Wed Jun 24 11:56:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/phi-3.5-Sakura-Yuzu-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74a46ff --- /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 +phi-3.5-Sakura-Yuzu.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-3.5-Sakura-Yuzu.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2f02dac --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: win10/phi-3.5-Sakura-Yuzu +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/win10/phi-3.5-Sakura-Yuzu + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#phi-3.5-Sakura-Yuzu-GGUF).*** + +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/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q3_K_M.gguf) | Q3_K_M | 2.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q3_K_L.gguf) | Q3_K_L | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q4_K_S.gguf) | Q4_K_S | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q4_K_M.gguf) | Q4_K_M | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q5_K_S.gguf) | Q5_K_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q6_K.gguf) | Q6_K | 3.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/phi-3.5-Sakura-Yuzu-GGUF/resolve/main/phi-3.5-Sakura-Yuzu.f16.gguf) | f16 | 7.7 | 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. + + diff --git a/phi-3.5-Sakura-Yuzu.IQ4_XS.gguf b/phi-3.5-Sakura-Yuzu.IQ4_XS.gguf new file mode 100644 index 0000000..89dcb16 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e12ce3f185b6bedbfa82f9e8d22b003aad17f8598a0e7193cb21b33c5845fa9 +size 2075583072 diff --git a/phi-3.5-Sakura-Yuzu.Q2_K.gguf b/phi-3.5-Sakura-Yuzu.Q2_K.gguf new file mode 100644 index 0000000..14f91d9 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eae15fd6765bce14af28d95eb42bdd28d999d453bf2d9e5f2421eb22ff47b2b +size 1416205920 diff --git a/phi-3.5-Sakura-Yuzu.Q3_K_L.gguf b/phi-3.5-Sakura-Yuzu.Q3_K_L.gguf new file mode 100644 index 0000000..fbf5311 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceb33f1fea33396d222411fb4fb14fe10553cf79acad2ed97640a06dc1237a5a +size 2087599200 diff --git a/phi-3.5-Sakura-Yuzu.Q3_K_M.gguf b/phi-3.5-Sakura-Yuzu.Q3_K_M.gguf new file mode 100644 index 0000000..ec54ac9 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e70c715cc04207e173262549639fbde0fb1b4d562ab8ca9de49b34af5e48fd5f +size 1955478624 diff --git a/phi-3.5-Sakura-Yuzu.Q3_K_S.gguf b/phi-3.5-Sakura-Yuzu.Q3_K_S.gguf new file mode 100644 index 0000000..a4d3871 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7289c6ff0adf43851d117bff0c19da00ea1a08d3a9f66d2b4078c86d37a5d279 +size 1681800288 diff --git a/phi-3.5-Sakura-Yuzu.Q4_K_M.gguf b/phi-3.5-Sakura-Yuzu.Q4_K_M.gguf new file mode 100644 index 0000000..ead5593 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528e37429b527d083308a4b21470c050e22e4b54aa87fcf399e38adc6ba8c4c1 +size 2393234016 diff --git a/phi-3.5-Sakura-Yuzu.Q4_K_S.gguf b/phi-3.5-Sakura-Yuzu.Q4_K_S.gguf new file mode 100644 index 0000000..0e9b88f --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8955ecd470248c0aec7dcd1a7381e195de573316f2234aa1e2d50b177736d49 +size 2188761696 diff --git a/phi-3.5-Sakura-Yuzu.Q5_K_M.gguf b/phi-3.5-Sakura-Yuzu.Q5_K_M.gguf new file mode 100644 index 0000000..94ba1d6 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61da3e009649d870ea1d170e90b437dad3a025ab552e8331c6e8ba7c4b05f896 +size 2815277664 diff --git a/phi-3.5-Sakura-Yuzu.Q5_K_S.gguf b/phi-3.5-Sakura-Yuzu.Q5_K_S.gguf new file mode 100644 index 0000000..fec8638 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c90dd1497749de3284179f633c3459d6265525ef59e189495d33a5918e6dede +size 2641476192 diff --git a/phi-3.5-Sakura-Yuzu.Q6_K.gguf b/phi-3.5-Sakura-Yuzu.Q6_K.gguf new file mode 100644 index 0000000..414dec8 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3378d70ba723aa8b6c3543928ed7dfe5a019656de7f039a27b9c9c62b7bc3987 +size 3135854688 diff --git a/phi-3.5-Sakura-Yuzu.Q8_0.gguf b/phi-3.5-Sakura-Yuzu.Q8_0.gguf new file mode 100644 index 0000000..95267d2 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d1c7d4e044b5d9cb9145345431b690c33198faca4fc50df0903e6d960e5b8cb +size 4061224032 diff --git a/phi-3.5-Sakura-Yuzu.f16.gguf b/phi-3.5-Sakura-Yuzu.f16.gguf new file mode 100644 index 0000000..fa303f0 --- /dev/null +++ b/phi-3.5-Sakura-Yuzu.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aed23206601f88380bfa029604c89ed39035807acd709770202e7c0d3d40de +size 7643298912