commit 4496581f8213afc6ccd8666c206ce9888e6598f3 Author: ModelHub XC Date: Sun Apr 12 14:11:56 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/QwQ-0.5B-Distilled-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4952931 --- /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 +QwQ-0.5B-Distilled-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QwQ-0.5B-Distilled-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QwQ-0.5B-Distilled-SFT.IQ4_XS.gguf b/QwQ-0.5B-Distilled-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..e09be32 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d75e7ba9e6abfabe8bc088454f2b9eb53e7ffffc1014a4d42d4dedf4d58ed78 +size 351446336 diff --git a/QwQ-0.5B-Distilled-SFT.Q2_K.gguf b/QwQ-0.5B-Distilled-SFT.Q2_K.gguf new file mode 100644 index 0000000..2b06036 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c3633e574ce070b4a2dca5cb65f9e766dd0d7488c0a4da558e8c9b898447d2 +size 338608448 diff --git a/QwQ-0.5B-Distilled-SFT.Q3_K_L.gguf b/QwQ-0.5B-Distilled-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..13b5635 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf4a28697063f896871e10e5c309f2bee3e70abbae4c0fe5f2e9c348a0b8d612 +size 369359168 diff --git a/QwQ-0.5B-Distilled-SFT.Q3_K_M.gguf b/QwQ-0.5B-Distilled-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..f770515 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a9b49b733f0057566dd8a38e8efc26ee4ad312053caeff4172b58b48f80983 +size 355467584 diff --git a/QwQ-0.5B-Distilled-SFT.Q3_K_S.gguf b/QwQ-0.5B-Distilled-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..8c2f276 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f686557c1874f36383a11165140640794a2db010b91db61fa3e1e423e034dc1 +size 338264384 diff --git a/QwQ-0.5B-Distilled-SFT.Q4_K_M.gguf b/QwQ-0.5B-Distilled-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..cc2de5b --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb15861871c636ccaa35dc27acf01d67e141d2808f5cdee5c451f5e647f3778e +size 397808960 diff --git a/QwQ-0.5B-Distilled-SFT.Q4_K_S.gguf b/QwQ-0.5B-Distilled-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..a07eb0c --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac07f25596134f44808eb24cc82febf05784c3bd6e606f09ce1ef50f457fdb1 +size 385472832 diff --git a/QwQ-0.5B-Distilled-SFT.Q5_K_M.gguf b/QwQ-0.5B-Distilled-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..8396d48 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:078f4ba0185d9432f43b6ea78e7abc90375b10ab81d9795be957c6e79d89c141 +size 420087104 diff --git a/QwQ-0.5B-Distilled-SFT.Q5_K_S.gguf b/QwQ-0.5B-Distilled-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..9857501 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9123fcc63433d3fc83a37b7a3fffa12c11993d35c6eeabd6feabff6ac9f24054 +size 412711232 diff --git a/QwQ-0.5B-Distilled-SFT.Q6_K.gguf b/QwQ-0.5B-Distilled-SFT.Q6_K.gguf new file mode 100644 index 0000000..84e189d --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a80e5eac79fbfa87d3564df25b0cbd193459e0854f8deff13757ee2170d69793 +size 505737536 diff --git a/QwQ-0.5B-Distilled-SFT.Q8_0.gguf b/QwQ-0.5B-Distilled-SFT.Q8_0.gguf new file mode 100644 index 0000000..f243f74 --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f7f1068c47f00090dc81aa932a62ba0d006f2c34821c939eb558d8164c2ab4 +size 531069248 diff --git a/QwQ-0.5B-Distilled-SFT.f16.gguf b/QwQ-0.5B-Distilled-SFT.f16.gguf new file mode 100644 index 0000000..4857e4c --- /dev/null +++ b/QwQ-0.5B-Distilled-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769f8deab92a2a03b019bb9d4c1c8654cbbb5880c2f21d9b7966a521b93df9a2 +size 994157888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e1fd5ba --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: kz919/QwQ-0.5B-Distilled-SFT +datasets: +- amphora/QwQ-LongCoT-130K-2 +- PowerInfer/QWQ-LONGCOT-500K +- PowerInfer/LONGCOT-Refine-500K +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/kz919/QwQ-0.5B-Distilled-SFT + + +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/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QwQ-0.5B-Distilled-SFT-GGUF/resolve/main/QwQ-0.5B-Distilled-SFT.f16.gguf) | f16 | 1.1 | 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. + +