commit ed5896168d89d2b30ffa1f767d5bee41b6a9f5d6 Author: ModelHub XC Date: Thu May 7 09:54:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..762ce8e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +VLAA-Thinker-Qwen2VL-2B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..19818fe --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: UCSC-VLAA/VLAA-Thinker-Qwen2VL-2B +language: +- en +library_name: transformers +license: cc-by-nc-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/UCSC-VLAA/VLAA-Thinker-Qwen2VL-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VLAA-Thinker-Qwen2VL-2B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-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/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.mmproj-fp16.gguf) | mmproj-fp16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-2B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-2B.f16.gguf) | f16 | 3.2 | 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/VLAA-Thinker-Qwen2VL-2B.IQ4_XS.gguf b/VLAA-Thinker-Qwen2VL-2B.IQ4_XS.gguf new file mode 100644 index 0000000..9774c54 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39601c6cf25c66cd668eda1ab58fc0d3e6c2d8e74b282863ec2033f37923c30f +size 902181408 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q2_K.gguf b/VLAA-Thinker-Qwen2VL-2B.Q2_K.gguf new file mode 100644 index 0000000..2bb3ebf --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22dd913b11e0b6187d69af0edcf86806e287c95f2fac54ad050f3f5b7aa3d30f +size 676303392 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q3_K_L.gguf b/VLAA-Thinker-Qwen2VL-2B.Q3_K_L.gguf new file mode 100644 index 0000000..b3009ef --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f82b64fa98dca7f419d607d8a61a350ae2e37bb515a9a904dd3d3985bfd28ad +size 880161312 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q3_K_M.gguf b/VLAA-Thinker-Qwen2VL-2B.Q3_K_M.gguf new file mode 100644 index 0000000..9934d51 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9376eb1e69ebdbe82afad2136df6096c2bccd63902a13327c256df73c737de +size 824177184 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q3_K_S.gguf b/VLAA-Thinker-Qwen2VL-2B.Q3_K_S.gguf new file mode 100644 index 0000000..d2fc1e4 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f92da5fb5c3cd61e51d87b5e22b8f7c0da2c9753be77aa8e91f5dcb75be16f +size 760943136 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q4_K_M.gguf b/VLAA-Thinker-Qwen2VL-2B.Q4_K_M.gguf new file mode 100644 index 0000000..30dd19e --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:733e60c579af8e61c630d0784a6f0d5b8b896ee5804cba20cbb9dd7957bf6d02 +size 986047008 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q4_K_S.gguf b/VLAA-Thinker-Qwen2VL-2B.Q4_K_S.gguf new file mode 100644 index 0000000..3f97c2c --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59e331fca743a5a85e7e82b29ce5be2060e8ffdf27695ee174b67b03e2fde3c7 +size 940311072 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q5_K_M.gguf b/VLAA-Thinker-Qwen2VL-2B.Q5_K_M.gguf new file mode 100644 index 0000000..754365e --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd75973e5138428ec9f253e9396f116724eb93b12cc3cb4e5aa45f67a56da338 +size 1125048864 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q5_K_S.gguf b/VLAA-Thinker-Qwen2VL-2B.Q5_K_S.gguf new file mode 100644 index 0000000..285edd9 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3bd0554f5bb17b967758b0eed212d469f71bbb39e034f73aaa0f910babf234c +size 1098727968 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q6_K.gguf b/VLAA-Thinker-Qwen2VL-2B.Q6_K.gguf new file mode 100644 index 0000000..f668188 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126c28d9cba120198781a775c5c6651b2c38cf0b6277980881c598aa9cbd0d98 +size 1272738336 diff --git a/VLAA-Thinker-Qwen2VL-2B.Q8_0.gguf b/VLAA-Thinker-Qwen2VL-2B.Q8_0.gguf new file mode 100644 index 0000000..4a59897 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ad7af3ab53f495e529767240538a5c816283d901e975091d2795a689fa061f +size 1646571552 diff --git a/VLAA-Thinker-Qwen2VL-2B.f16.gguf b/VLAA-Thinker-Qwen2VL-2B.f16.gguf new file mode 100644 index 0000000..0e56f83 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1da0ac8b371d98e19ea6c6a99634397f2ccf9909b0d938a8ffe6e8c57fbc9f +size 3093667872 diff --git a/VLAA-Thinker-Qwen2VL-2B.mmproj-fp16.gguf b/VLAA-Thinker-Qwen2VL-2B.mmproj-fp16.gguf new file mode 100644 index 0000000..3049f0f --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-2B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5721fa76c5a816958d06a761098cbd5c7c9ffcd53938cc270f759e506908ed36 +size 1331656192