commit f4b5a09bd97e1728bc147cf3ba4521cae4e4235a Author: ModelHub XC Date: Thu Jul 23 23:22:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-Reranker-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bb9f2e7 --- /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-Reranker-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Reranker-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-Reranker-8B.IQ4_XS.gguf b/Qwen3-Reranker-8B.IQ4_XS.gguf new file mode 100644 index 0000000..a04d8e5 --- /dev/null +++ b/Qwen3-Reranker-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56754719dacdbb0a0b04f594a70ea3e5bb263d60815711434b807a5cf0281d96 +size 4591812640 diff --git a/Qwen3-Reranker-8B.Q2_K.gguf b/Qwen3-Reranker-8B.Q2_K.gguf new file mode 100644 index 0000000..7a031d0 --- /dev/null +++ b/Qwen3-Reranker-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6407c07a6960ea3525dc626cef3ab0ff2fe6b7599ead3bb21459501cca380638 +size 3280471008 diff --git a/Qwen3-Reranker-8B.Q3_K_L.gguf b/Qwen3-Reranker-8B.Q3_K_L.gguf new file mode 100644 index 0000000..eee196f --- /dev/null +++ b/Qwen3-Reranker-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba8f2d9cd7acbd926fb5efa99f660bad35a5b4fd79ef7e709e00ed30b895937a +size 4430021120 diff --git a/Qwen3-Reranker-8B.Q3_K_M.gguf b/Qwen3-Reranker-8B.Q3_K_M.gguf new file mode 100644 index 0000000..7def95b --- /dev/null +++ b/Qwen3-Reranker-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad72cbb48f0380751727ca200c5a90be3382cfacd2aada4d74ad4968bd77fd40 +size 4122788352 diff --git a/Qwen3-Reranker-8B.Q3_K_S.gguf b/Qwen3-Reranker-8B.Q3_K_S.gguf new file mode 100644 index 0000000..94d0578 --- /dev/null +++ b/Qwen3-Reranker-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39babf8bfe12949d2f2abfdb09ffc7beb10c9cf0f1bae927e8a837e48adae763 +size 3768238592 diff --git a/Qwen3-Reranker-8B.Q4_K_M.gguf b/Qwen3-Reranker-8B.Q4_K_M.gguf new file mode 100644 index 0000000..fcf9e19 --- /dev/null +++ b/Qwen3-Reranker-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b683a127768786c0ccd87859b21a2c061ea70f30a7d14efd4476683854eea197 +size 5026265760 diff --git a/Qwen3-Reranker-8B.Q4_K_S.gguf b/Qwen3-Reranker-8B.Q4_K_S.gguf new file mode 100644 index 0000000..2e8a2b7 --- /dev/null +++ b/Qwen3-Reranker-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac08c98dc10cedb972969141fc9726f94458082dcc0dab82d30012493eeb3923 +size 4800494240 diff --git a/Qwen3-Reranker-8B.Q5_K_M.gguf b/Qwen3-Reranker-8B.Q5_K_M.gguf new file mode 100644 index 0000000..260f13e --- /dev/null +++ b/Qwen3-Reranker-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78a9fc0c2f24a5a00a5be558f4ff81a5e7296ad4b24e1223bfbe4a2dc7efe09e +size 5849457824 diff --git a/Qwen3-Reranker-8B.Q5_K_S.gguf b/Qwen3-Reranker-8B.Q5_K_S.gguf new file mode 100644 index 0000000..0351dd7 --- /dev/null +++ b/Qwen3-Reranker-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ba29c31b14635dd35723bd8edaa81e6f8e2119dd2d4eea791c29619c921b655 +size 5719106720 diff --git a/Qwen3-Reranker-8B.Q6_K.gguf b/Qwen3-Reranker-8B.Q6_K.gguf new file mode 100644 index 0000000..9174710 --- /dev/null +++ b/Qwen3-Reranker-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06b2ae36091876f8e4b0733c653e822b75cf4f2d6437fd34ee32886d16fcdb6c +size 6724099392 diff --git a/Qwen3-Reranker-8B.Q8_0.gguf b/Qwen3-Reranker-8B.Q8_0.gguf new file mode 100644 index 0000000..03ca58f --- /dev/null +++ b/Qwen3-Reranker-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba16c501a74929b6c9f71033420172c028b85e216f8d03bef1c9a758fbf3f71a +size 8707188736 diff --git a/Qwen3-Reranker-8B.f16.gguf b/Qwen3-Reranker-8B.f16.gguf new file mode 100644 index 0000000..ceebcab --- /dev/null +++ b/Qwen3-Reranker-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56bd67992a7a1eba2f9f7d598f4a1b818f39be466c02900bba50899f91868853 +size 16383663616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e014d4f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Qwen/Qwen3-Reranker-8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sentence-transformers +--- +## About + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-Reranker-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Reranker-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-Reranker-8B-i1-GGUF +## 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-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Reranker-8B-GGUF/resolve/main/Qwen3-Reranker-8B.f16.gguf) | f16 | 16.5 | 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. + +