commit b233ef05b36a3c8fa805829c5c788010408207a9 Author: ModelHub XC Date: Mon May 11 10:36:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7a62b47 --- /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-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-1.7B-Yukari-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-1.7B-Yukari-SFT.IQ4_XS.gguf b/Qwen3-1.7B-Yukari-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..0ee8cf2 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a76ba5c665eb927c304a6114f0b428dd75dc18cb43a3e93104da94279d8ef076 +size 1016281856 diff --git a/Qwen3-1.7B-Yukari-SFT.Q2_K.gguf b/Qwen3-1.7B-Yukari-SFT.Q2_K.gguf new file mode 100644 index 0000000..c1bddf9 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c3d62e34d1a5f8b38927a2e6ffd54ba63b3fe7feb1f9db206110fa21b66fa5 +size 777796352 diff --git a/Qwen3-1.7B-Yukari-SFT.Q3_K_L.gguf b/Qwen3-1.7B-Yukari-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..567b08a --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1c733317fed3f0266237b82dcd6ea7a644d6541c5f44195ecaef53a6dfb143b +size 1003502336 diff --git a/Qwen3-1.7B-Yukari-SFT.Q3_K_M.gguf b/Qwen3-1.7B-Yukari-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..e6130f8 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4eaa870ebed324eaeac75655a0bfbb55dde1b313d4d25b96b2412ff17ddf84 +size 939539200 diff --git a/Qwen3-1.7B-Yukari-SFT.Q3_K_S.gguf b/Qwen3-1.7B-Yukari-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..e4cbd29 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e046f6bac5d4443ac94d7b47541eaa827a312b04c34709b045580dd3eef78110 +size 867252992 diff --git a/Qwen3-1.7B-Yukari-SFT.Q4_K_M.gguf b/Qwen3-1.7B-Yukari-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..53b0551 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14785820d96e278fce5332d7b843cf56d5e1272f121ddc174b4ca6ecd5487bf9 +size 1107409664 diff --git a/Qwen3-1.7B-Yukari-SFT.Q4_K_S.gguf b/Qwen3-1.7B-Yukari-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..a7af623 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099b5b41398478a922765f4165be60e8f970855529157b8ca84688571780fdbf +size 1060190976 diff --git a/Qwen3-1.7B-Yukari-SFT.Q5_K_M.gguf b/Qwen3-1.7B-Yukari-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..9a232af --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ca7e35bbeaf5d56afd795a5b4969529e4d9d515d1f9d23b0daecb67f5ebfbe +size 1257880320 diff --git a/Qwen3-1.7B-Yukari-SFT.Q5_K_S.gguf b/Qwen3-1.7B-Yukari-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..37277ee --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880963f670286c0b4d9cdfad212f0962a370c3e8c61cea929fd6f5906846787b +size 1230584576 diff --git a/Qwen3-1.7B-Yukari-SFT.Q6_K.gguf b/Qwen3-1.7B-Yukari-SFT.Q6_K.gguf new file mode 100644 index 0000000..4eb986a --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc248d6fc6d872f775fb4e8d49ad18c2b50f2e2436be7902997ba3a8ab40a25 +size 1417755392 diff --git a/Qwen3-1.7B-Yukari-SFT.Q8_0.gguf b/Qwen3-1.7B-Yukari-SFT.Q8_0.gguf new file mode 100644 index 0000000..d8e452f --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f8a6e4abd4363e39ce75ceddb290bfcb8c27884105ecff35c8a95d6ab82356 +size 1834427136 diff --git a/Qwen3-1.7B-Yukari-SFT.f16.gguf b/Qwen3-1.7B-Yukari-SFT.f16.gguf new file mode 100644 index 0000000..6424e16 --- /dev/null +++ b/Qwen3-1.7B-Yukari-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4e6b7424defdb0638c3b85708c855fe0de553f7b4406fd0b6aabd912176f424 +size 3447350016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f3168c7 --- /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-SFT-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-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-1.7B-Yukari-SFT-GGUF/resolve/main/Qwen3-1.7B-Yukari-SFT.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. + +