commit c4140da9cc2354bfa8434883f97feba1be85f363 Author: ModelHub XC Date: Wed Jul 29 05:07:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-VL-Reranker-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9d4f4b8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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-VL-Reranker-2B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-VL-Reranker-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-VL-Reranker-2B.IQ4_XS.gguf b/Qwen3-VL-Reranker-2B.IQ4_XS.gguf new file mode 100644 index 0000000..44f9965 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9389be132439b5cb7ffb1530409ac48df5711c0f746614313e38e3a958510761 +size 1016282976 diff --git a/Qwen3-VL-Reranker-2B.Q2_K.gguf b/Qwen3-VL-Reranker-2B.Q2_K.gguf new file mode 100644 index 0000000..32a8049 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07bc44f468ecb3b2427e725f2925d4296c0fb0693da66b278136220aa4fce31 +size 777797472 diff --git a/Qwen3-VL-Reranker-2B.Q3_K_L.gguf b/Qwen3-VL-Reranker-2B.Q3_K_L.gguf new file mode 100644 index 0000000..08db8c4 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5dd88d5ab4ae413e98671f0ab2d127e52605100a9a678ccd3089f3a67823ba0 +size 1003503456 diff --git a/Qwen3-VL-Reranker-2B.Q3_K_M.gguf b/Qwen3-VL-Reranker-2B.Q3_K_M.gguf new file mode 100644 index 0000000..ed3d322 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaca84d2db0dc2130c18f3f626845cb9657a670342d1fb3a382462972216d388 +size 939540320 diff --git a/Qwen3-VL-Reranker-2B.Q3_K_S.gguf b/Qwen3-VL-Reranker-2B.Q3_K_S.gguf new file mode 100644 index 0000000..1ed7f39 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aec447a7db24f2090d8d1c970cf696728e456afdccf00925020bc24bfcac954 +size 867254112 diff --git a/Qwen3-VL-Reranker-2B.Q4_K_M.gguf b/Qwen3-VL-Reranker-2B.Q4_K_M.gguf new file mode 100644 index 0000000..a876579 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c2472ca5a85b815ecbcb1f74acd7e8930951f738c4e9d501153b6b4315d642 +size 1107410784 diff --git a/Qwen3-VL-Reranker-2B.Q4_K_S.gguf b/Qwen3-VL-Reranker-2B.Q4_K_S.gguf new file mode 100644 index 0000000..573c18d --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5faf8fbddc8840471cf9925f04dfe34612fa07ca838fe1b8a9ea947dedbffb56 +size 1060192096 diff --git a/Qwen3-VL-Reranker-2B.Q5_K_M.gguf b/Qwen3-VL-Reranker-2B.Q5_K_M.gguf new file mode 100644 index 0000000..dd6e17f --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5389fa85210792300c4abcd096af6772365b737b42ddeaf943e2c2b5c4c65beb +size 1257881440 diff --git a/Qwen3-VL-Reranker-2B.Q5_K_S.gguf b/Qwen3-VL-Reranker-2B.Q5_K_S.gguf new file mode 100644 index 0000000..a7935b8 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61342ad99e9c193ca2eccfc4907f72102393561f3610f2bee80f00fe6cadb5cf +size 1230585696 diff --git a/Qwen3-VL-Reranker-2B.Q6_K.gguf b/Qwen3-VL-Reranker-2B.Q6_K.gguf new file mode 100644 index 0000000..d368ab6 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02561749781094dfdd27c34678fc97def5ee5e6c7d6b16e89df47ff453caef75 +size 1417756512 diff --git a/Qwen3-VL-Reranker-2B.Q8_0.gguf b/Qwen3-VL-Reranker-2B.Q8_0.gguf new file mode 100644 index 0000000..82ee1a3 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f237a076d3aeb1470816f524bff337d1a7aaa9c4760de2a78c227506db1b70b6 +size 1834428256 diff --git a/Qwen3-VL-Reranker-2B.f16.gguf b/Qwen3-VL-Reranker-2B.f16.gguf new file mode 100644 index 0000000..0496d60 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0921ea8b82255907c138717e7d3c5b6e96f08f55270358c94d234f75a16c5054 +size 3447351136 diff --git a/Qwen3-VL-Reranker-2B.mmproj-Q8_0.gguf b/Qwen3-VL-Reranker-2B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..d91d4d0 --- /dev/null +++ b/Qwen3-VL-Reranker-2B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528a7f4c39851c2fc5bf128d73437c1b73e86fb4df41442781c804806a687980 +size 445053600 diff --git a/Qwen3-VL-Reranker-2B.mmproj-f16.gguf b/Qwen3-VL-Reranker-2B.mmproj-f16.gguf new file mode 100644 index 0000000..680a5df --- /dev/null +++ b/Qwen3-VL-Reranker-2B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d38b7ae347fc3e51726bfb9cba1b04885f1f005a4087d8070933e46509db5a6e +size 819395232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..91c9e86 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Qwen/Qwen3-VL-Reranker-2B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sentence-transformers +- transformers +- multimodal rerank +- text rerank +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Qwen/Qwen3-VL-Reranker-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-VL-Reranker-2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-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-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-VL-Reranker-2B-GGUF/resolve/main/Qwen3-VL-Reranker-2B.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. + +