commit ce5e57e70c22ecd6c139f33d42b102e6707e7ff3 Author: ModelHub XC Date: Fri May 8 16:01:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-1.7B-Yukari-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..faeee9e --- /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 +Qwen3-1.7B-Yukari.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-1.7B-Yukari.IQ4_XS.gguf b/Qwen3-1.7B-Yukari.IQ4_XS.gguf new file mode 100644 index 0000000..043c472 --- /dev/null +++ b/Qwen3-1.7B-Yukari.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8de957354ed0f98cb73b1d9c008459bce39eda788e0a5e9787b05a027248d3 +size 1016281824 diff --git a/Qwen3-1.7B-Yukari.Q2_K.gguf b/Qwen3-1.7B-Yukari.Q2_K.gguf new file mode 100644 index 0000000..73f4250 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0fb672943fb474f32c7232487a343f16af528918218e65ddc362da6963cb621 +size 777796320 diff --git a/Qwen3-1.7B-Yukari.Q3_K_L.gguf b/Qwen3-1.7B-Yukari.Q3_K_L.gguf new file mode 100644 index 0000000..3ec8415 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f6ed3d5911f6a05540d6c5c8962a96002d1b608b9147f32d42e8db7f6c87ae +size 1003502304 diff --git a/Qwen3-1.7B-Yukari.Q3_K_M.gguf b/Qwen3-1.7B-Yukari.Q3_K_M.gguf new file mode 100644 index 0000000..c277b0c --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e961533d7d271c507c7e55b7c22d68a8630934b75c9c378165dad836cda36f73 +size 939539168 diff --git a/Qwen3-1.7B-Yukari.Q3_K_S.gguf b/Qwen3-1.7B-Yukari.Q3_K_S.gguf new file mode 100644 index 0000000..e0a5671 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9aa6ffb2215b553eaaf2deb63d84fe0f1316b5b6a008fa7ab85fc5e623d56f +size 867252960 diff --git a/Qwen3-1.7B-Yukari.Q4_K_M.gguf b/Qwen3-1.7B-Yukari.Q4_K_M.gguf new file mode 100644 index 0000000..7a9932c --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005c5bd0f76f4158e70297b4805d4d77e8e2191c7ce035714a016e1cdca59c86 +size 1107409632 diff --git a/Qwen3-1.7B-Yukari.Q4_K_S.gguf b/Qwen3-1.7B-Yukari.Q4_K_S.gguf new file mode 100644 index 0000000..39d609f --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d937ddd9de635637e762914a8453a58a478dd0ca24bb17aad07b20cc5e41a05 +size 1060190944 diff --git a/Qwen3-1.7B-Yukari.Q5_K_M.gguf b/Qwen3-1.7B-Yukari.Q5_K_M.gguf new file mode 100644 index 0000000..512f0be --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f78271b25a31f8deac8b8f1bb563ad3300ffa40b5c99e6f266f13debf888ec2 +size 1257880288 diff --git a/Qwen3-1.7B-Yukari.Q5_K_S.gguf b/Qwen3-1.7B-Yukari.Q5_K_S.gguf new file mode 100644 index 0000000..b9ba814 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec9ef72b30f5d64f22e699f8437a9f85bbe362fe4cac8d6425dea444a0bd57f7 +size 1230584544 diff --git a/Qwen3-1.7B-Yukari.Q6_K.gguf b/Qwen3-1.7B-Yukari.Q6_K.gguf new file mode 100644 index 0000000..3d39970 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44c63a95392daa51e136a4faf0c9dee0e2acaf7ba8bb3f3b898e0a46430e1159 +size 1417755360 diff --git a/Qwen3-1.7B-Yukari.Q8_0.gguf b/Qwen3-1.7B-Yukari.Q8_0.gguf new file mode 100644 index 0000000..f3c9501 --- /dev/null +++ b/Qwen3-1.7B-Yukari.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d679b4d382904b56a8a28dc143bbfadc721eb78ff1c7c08589f33be0d83f58 +size 1834427104 diff --git a/Qwen3-1.7B-Yukari.f16.gguf b/Qwen3-1.7B-Yukari.f16.gguf new file mode 100644 index 0000000..57591f3 --- /dev/null +++ b/Qwen3-1.7B-Yukari.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1686ebc3caef5af0c17dc7246b4c1c19d12efbf60e7eba082eb0f1fbdfd1791f +size 3447349984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1e7d1be --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: zzoceanpie/Qwen3-1.7B-Yukari-SFT +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- qlora +- roleplay +- qwen +- sft +- touhou +- character-roleplay +- synthetic-data +- generated_from_trainer +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zzoceanpie/Qwen3-1.7B-Yukari-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-1.7B-Yukari-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/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-GGUF/resolve/main/Qwen3-1.7B-Yukari.f16.gguf) | f16 | 3.5 | 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. + +