commit c6ae0369e65b0f6c47c12276a695e2ca89ecbab6 Author: ModelHub XC Date: Mon Jul 20 19:38:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-polite-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b0e7f77 --- /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-polite.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-polite.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..458e983 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: reshinthadith/qwen3-polite +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/reshinthadith/qwen3-polite + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-polite-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-polite-GGUF/resolve/main/qwen3-polite.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-polite-GGUF/resolve/main/qwen3-polite.f16.gguf) | f16 | 1.3 | 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/qwen3-polite.IQ4_XS.gguf b/qwen3-polite.IQ4_XS.gguf new file mode 100644 index 0000000..e180d57 --- /dev/null +++ b/qwen3-polite.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f37ecd98c946c697daaa99f42e48f19bfdad845d33b22731e95d89cb152a701 +size 369278048 diff --git a/qwen3-polite.Q2_K.gguf b/qwen3-polite.Q2_K.gguf new file mode 100644 index 0000000..d6f2d09 --- /dev/null +++ b/qwen3-polite.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee2838fc53a5899a0a557f3e0cebfd7d41f1704f8460db5a90ec72f18fd84cc3 +size 296238176 diff --git a/qwen3-polite.Q3_K_L.gguf b/qwen3-polite.Q3_K_L.gguf new file mode 100644 index 0000000..a921eba --- /dev/null +++ b/qwen3-polite.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85e6a79c5d997683b2717a821053ce42c7833e6d215e76aa383d0ffc08098147 +size 368491616 diff --git a/qwen3-polite.Q3_K_M.gguf b/qwen3-polite.Q3_K_M.gguf new file mode 100644 index 0000000..d5f7622 --- /dev/null +++ b/qwen3-polite.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd7f4c981028431ed1de2a9e636b72eb5ca059ded387e85164254b3bec460f3 +size 347126880 diff --git a/qwen3-polite.Q3_K_S.gguf b/qwen3-polite.Q3_K_S.gguf new file mode 100644 index 0000000..4df4ae5 --- /dev/null +++ b/qwen3-polite.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cec566fb33d564a9ca5c933123583d653802468ccf40f2265ea6a91d1c97f95 +size 323075168 diff --git a/qwen3-polite.Q4_K_M.gguf b/qwen3-polite.Q4_K_M.gguf new file mode 100644 index 0000000..c2737b4 --- /dev/null +++ b/qwen3-polite.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b96cedd51149ddb120493816c1f0b40444dbbb06ae1a10c51a159a9047a1e0c +size 396704864 diff --git a/qwen3-polite.Q4_K_S.gguf b/qwen3-polite.Q4_K_S.gguf new file mode 100644 index 0000000..f4f580d --- /dev/null +++ b/qwen3-polite.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537eea12102649c0bb0d70f02578f3ba8c72164e8ae9ae38925e6416ae4a2fde +size 383269984 diff --git a/qwen3-polite.Q5_K_M.gguf b/qwen3-polite.Q5_K_M.gguf new file mode 100644 index 0000000..c9bea9f --- /dev/null +++ b/qwen3-polite.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a335d19b86df1a2524c47a19274ef6aa6b5e5c3eb9f01268ac0cf9d56b05a1b0 +size 444415072 diff --git a/qwen3-polite.Q5_K_S.gguf b/qwen3-polite.Q5_K_S.gguf new file mode 100644 index 0000000..1fb4f61 --- /dev/null +++ b/qwen3-polite.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d683483cd2ad8286379f656c4fa61971175d8b606225aee5b1d7684817c0522b +size 436616288 diff --git a/qwen3-polite.Q6_K.gguf b/qwen3-polite.Q6_K.gguf new file mode 100644 index 0000000..502957c --- /dev/null +++ b/qwen3-polite.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55fe72b8c2fbc0475664f119f5841c1800e793b9e11812a225244374e37e59d8 +size 495107168 diff --git a/qwen3-polite.Q8_0.gguf b/qwen3-polite.Q8_0.gguf new file mode 100644 index 0000000..0d18ff7 --- /dev/null +++ b/qwen3-polite.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e5f49044ec7b0d7a428cdc7657a8a9d1457856d68a030d572b4901c92e8f529 +size 639447136 diff --git a/qwen3-polite.f16.gguf b/qwen3-polite.f16.gguf new file mode 100644 index 0000000..3d52def --- /dev/null +++ b/qwen3-polite.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f09296d8b78e7f930040d4fcafc79aec3bdcb8381cda1b08170ee8be2ff0c444 +size 1198182496