commit f5b0f539495d3ceb68a2d7da4a9af56e4c000d65 Author: ModelHub XC Date: Sun Aug 16 15:09:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..875d16f --- /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-7B.mmproj-fp16.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLAA-Thinker-Qwen2VL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d51229 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/UCSC-VLAA/VLAA-Thinker-Qwen2VL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VLAA-Thinker-Qwen2VL-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-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-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.mmproj-fp16.gguf) | mmproj-fp16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/VLAA-Thinker-Qwen2VL-7B-GGUF/resolve/main/VLAA-Thinker-Qwen2VL-7B.f16.gguf) | f16 | 15.3 | 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/VLAA-Thinker-Qwen2VL-7B.IQ4_XS.gguf b/VLAA-Thinker-Qwen2VL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..50c695a --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f003e2308151b19427133eca75d2326bddb7204ce0334416959ae1853eae5ef3 +size 4250297344 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q2_K.gguf b/VLAA-Thinker-Qwen2VL-7B.Q2_K.gguf new file mode 100644 index 0000000..95542fe --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55141cd36f25ea54b8905b8bbf3cb95510a7c0623944c4bd6b0e4b57d4dbe902 +size 3015939072 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q3_K_L.gguf b/VLAA-Thinker-Qwen2VL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..2f1d3bf --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bd141fdfa4ab6439b4df54dbc6f64508b6ce4b6d1ff313c5bb404361bcbd9a +size 4088458240 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q3_K_M.gguf b/VLAA-Thinker-Qwen2VL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..92b5e11 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9869ca708b7d3b1503ed580205605f8ed794855e154aa0be378a8b879b0ed8c +size 3808390144 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q3_K_S.gguf b/VLAA-Thinker-Qwen2VL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..4bc08af --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b547e26b7a94bc8b907fd26c2949be216ae300beec20015011fb2386f3da12 +size 3492367360 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q4_K_M.gguf b/VLAA-Thinker-Qwen2VL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..7c66ff3 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f397793548916cb589c0dcb95c05974b6fa924178403f91cf3c9560e3e8d96a +size 4683072512 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q4_K_S.gguf b/VLAA-Thinker-Qwen2VL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..0ec5130 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac299fc2596dd0abfafb7ef240e560c0e541c59f447be0de423e9d7857b62e56 +size 4457767936 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q5_K_M.gguf b/VLAA-Thinker-Qwen2VL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..966346f --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969ca0a0024cc1a1d7510f9925e2cb1f12e7191e8c128dff6c18aaeaa44d952e +size 5444830208 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q5_K_S.gguf b/VLAA-Thinker-Qwen2VL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..b3d2ad5 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bfec6990fe443271e9b815f480d1bee4cc7e878d0f8dd3659aa24bee3d3278 +size 5315175424 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q6_K.gguf b/VLAA-Thinker-Qwen2VL-7B.Q6_K.gguf new file mode 100644 index 0000000..7c9110e --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87248baccf0afd28dfbded396f7455c621c3a08277ff3944a34ac6c72bef92e8 +size 6254197760 diff --git a/VLAA-Thinker-Qwen2VL-7B.Q8_0.gguf b/VLAA-Thinker-Qwen2VL-7B.Q8_0.gguf new file mode 100644 index 0000000..88899e6 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:425cdf09d63c3ec9b9b542964f12b92854e8ef162f722ed9243533280d428ca4 +size 8098524160 diff --git a/VLAA-Thinker-Qwen2VL-7B.f16.gguf b/VLAA-Thinker-Qwen2VL-7B.f16.gguf new file mode 100644 index 0000000..588ada8 --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06d830b43bead66b2ea04d2ce59504270520afa97c65afe3d089d078ac2b8ca +size 15237852160 diff --git a/VLAA-Thinker-Qwen2VL-7B.mmproj-fp16.gguf b/VLAA-Thinker-Qwen2VL-7B.mmproj-fp16.gguf new file mode 100644 index 0000000..080175e --- /dev/null +++ b/VLAA-Thinker-Qwen2VL-7B.mmproj-fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0324de08d3fabc758f0f20516b748752917dd40ea65ca2a04e10a5310edf1928 +size 1352635904