commit fbec48bdbab9781e23c3460f33ddef6ded238d04 Author: ModelHub XC Date: Sun Sep 27 15:05:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d18fe3c --- /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 +TEMPURA-Qwen2.5-VL-3B-s2.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..ef1990c --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: andaba/TEMPURA-Qwen2.5-VL-3B-s2 +datasets: +- andaba/TEMPURA-VER +language: +- en +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/andaba/TEMPURA-Qwen2.5-VL-3B-s2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TEMPURA-Qwen2.5-VL-3B-s2-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/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s2-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s2.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. + + diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.IQ4_XS.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.IQ4_XS.gguf new file mode 100644 index 0000000..8d1761c --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ece90610fcc3efd4670f72865422432fa25a5a47e101e912b7fcf92ecb30e6f +size 1753186016 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q2_K.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q2_K.gguf new file mode 100644 index 0000000..6c7a53e --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8710e56289bff3981c7316f2495c51d5ff0fbfe91fb7a8c6c8aa0527f3d007 +size 1274756832 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_L.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_L.gguf new file mode 100644 index 0000000..0b814ce --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b938758c1f618e48979fe9cf225542a39d427e5bc10887ead3a74b9ae56a6743 +size 1707392736 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_M.gguf new file mode 100644 index 0000000..3db6e1c --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde19239bbacfbe9bb5390f0c00040d9537db950e22504e8e7a4b98dc372885b +size 1590476512 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_S.gguf new file mode 100644 index 0000000..83e42b9 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae03781567556e85495ce6d3bb6b9c3d08f0e67eb0667216523e557f5a3b6edb +size 1454358240 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_M.gguf new file mode 100644 index 0000000..2987fb4 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dbb8b6856572e163bfafd0522b13be37bcd711b474f8d328437828e39d5eeeb +size 1929903840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_S.gguf new file mode 100644 index 0000000..02f5705 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fad419e33b1c0eb1bd35895cbf9c7ce33142ce9b802b39b84c465486a6240a5 +size 1834385120 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_M.gguf new file mode 100644 index 0000000..0fc7d15 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d357a18f64077d5a2662d122b2371c6e421c2093b4249be121aac681ee56aa3e +size 2224815840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_S.gguf new file mode 100644 index 0000000..f6541a6 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:786891eddf60ad8f8c36b625acb00e065747242eaa8e66cd48a8e39a22538cee +size 2169667296 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q6_K.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q6_K.gguf new file mode 100644 index 0000000..c464705 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38037773b55c0c16a3157505eb50bec8b604288e70b3d99759110a7900c706d2 +size 2538159840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.Q8_0.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.Q8_0.gguf new file mode 100644 index 0000000..7ad9cad --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b25726e01e3be6530e1dea5aeb3c9ce54932bb8e33019ba7f66a916007fbc74 +size 3285477088 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.f16.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.f16.gguf new file mode 100644 index 0000000..96f366a --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83eb9fc322a283c5d420eb0d2b16681890e047d216466b069fdade1a8645d0a4 +size 6178318048 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-Q8_0.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-Q8_0.gguf new file mode 100644 index 0000000..26176f5 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a491d47b658066f6d1690ef1529e2f199ff5eeb3cf78e1e4eaa4b60f57183cd +size 844758624 diff --git a/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-f16.gguf b/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-f16.gguf new file mode 100644 index 0000000..f026ac1 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s2.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e8e0cff4c3f742d9db3532970b89dd75124934e8ff56ff3bed651e46754081f +size 1338429024