commit 12b881e88d8d35f17239ba9f69364146244c63a0 Author: ModelHub XC Date: Sat May 9 04:34:51 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/4v-distill-Qwen2.5VL-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c0fcb3a --- /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 +4v-distill-Qwen2.5VL-3B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +4v-distill-Qwen2.5VL-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/4v-distill-Qwen2.5VL-3B.IQ4_XS.gguf b/4v-distill-Qwen2.5VL-3B.IQ4_XS.gguf new file mode 100644 index 0000000..2147e95 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a18871f99b6be2c77e26a8a0d712707148048676d0692cc79cba0d872031a13 +size 1753184032 diff --git a/4v-distill-Qwen2.5VL-3B.Q2_K.gguf b/4v-distill-Qwen2.5VL-3B.Q2_K.gguf new file mode 100644 index 0000000..27a5f8a --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dea4e274cc06d8bdac68443516045e9449455119a132f22cc76d0e43f859ab1 +size 1274754848 diff --git a/4v-distill-Qwen2.5VL-3B.Q3_K_L.gguf b/4v-distill-Qwen2.5VL-3B.Q3_K_L.gguf new file mode 100644 index 0000000..c3c7de8 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ade4d7563e5d0ada2d77a404da82f81408dcbc12c00ed4f6d0b0c132deab41b +size 1707390752 diff --git a/4v-distill-Qwen2.5VL-3B.Q3_K_M.gguf b/4v-distill-Qwen2.5VL-3B.Q3_K_M.gguf new file mode 100644 index 0000000..c12d426 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7448554b1e5b111a1346445d60256bc5172aa929790f0409929652484fefa07a +size 1590474528 diff --git a/4v-distill-Qwen2.5VL-3B.Q3_K_S.gguf b/4v-distill-Qwen2.5VL-3B.Q3_K_S.gguf new file mode 100644 index 0000000..086e6a8 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eec64b268e4f6f19120a8a973f8cc61f23d10f47e46eb2aeede5aacb469209ed +size 1454356256 diff --git a/4v-distill-Qwen2.5VL-3B.Q4_K_M.gguf b/4v-distill-Qwen2.5VL-3B.Q4_K_M.gguf new file mode 100644 index 0000000..02bef09 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2929aec4d55bb71c709effe0d383757bfc69e59e9388624aa8ec49a7a712a90 +size 1929901856 diff --git a/4v-distill-Qwen2.5VL-3B.Q4_K_S.gguf b/4v-distill-Qwen2.5VL-3B.Q4_K_S.gguf new file mode 100644 index 0000000..1f52a55 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7066f2d030a2bf5ea8d22b0bb2d9107641f34c0ea62234abd42c9bfef7e865ac +size 1834383136 diff --git a/4v-distill-Qwen2.5VL-3B.Q5_K_M.gguf b/4v-distill-Qwen2.5VL-3B.Q5_K_M.gguf new file mode 100644 index 0000000..0533f3f --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922072f88025204c4af851b04ae855cd52b94b2a7802d1a79e06466468f17eb5 +size 2224813856 diff --git a/4v-distill-Qwen2.5VL-3B.Q5_K_S.gguf b/4v-distill-Qwen2.5VL-3B.Q5_K_S.gguf new file mode 100644 index 0000000..93cc6a1 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5794046dafb5c67e1dce5bdc7a17d69a6039090acc5e00c7ded7f3f1399648e7 +size 2169665312 diff --git a/4v-distill-Qwen2.5VL-3B.Q6_K.gguf b/4v-distill-Qwen2.5VL-3B.Q6_K.gguf new file mode 100644 index 0000000..9ba131c --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b58898f576d8eebd7a533850caccaa9b4a7b3ab5f803d142f94444da54ad7e +size 2538157856 diff --git a/4v-distill-Qwen2.5VL-3B.Q8_0.gguf b/4v-distill-Qwen2.5VL-3B.Q8_0.gguf new file mode 100644 index 0000000..7c6476f --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e3513db71156f32790de1aa82f775029e87de144a9bbad6572d1fae0c1147b4 +size 3285475104 diff --git a/4v-distill-Qwen2.5VL-3B.f16.gguf b/4v-distill-Qwen2.5VL-3B.f16.gguf new file mode 100644 index 0000000..337cd6c --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea9163eca95a0309d5983e18218e134a37b176501349f635ff324c9fa4e3f8c5 +size 6178316064 diff --git a/4v-distill-Qwen2.5VL-3B.mmproj-Q8_0.gguf b/4v-distill-Qwen2.5VL-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..01ec3aa --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b987df30f886af55fce99e1637ee181bd3b2340f955ff262ed722bb818aa0cc +size 844758048 diff --git a/4v-distill-Qwen2.5VL-3B.mmproj-f16.gguf b/4v-distill-Qwen2.5VL-3B.mmproj-f16.gguf new file mode 100644 index 0000000..d81f143 --- /dev/null +++ b/4v-distill-Qwen2.5VL-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:857019c6d7537f4a40a26764f537b6faaafbaca9295ba7a44d82886712da04ec +size 1338428448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..87daddf --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: yan111222/4v-distill-Qwen2.5VL-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/yan111222/4v-distill-Qwen2.5VL-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#4v-distill-Qwen2.5VL-3B-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/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/4v-distill-Qwen2.5VL-3B-GGUF/resolve/main/4v-distill-Qwen2.5VL-3B.f16.gguf) | f16 | 6.3 | 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. + +