commit 31e6fca9d768752acc9c5739f8e24e33e0b8f528 Author: ModelHub XC Date: Tue May 12 20:44:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2389873 --- /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-s1.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +TEMPURA-Qwen2.5-VL-3B-s1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9fe954b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: andaba/TEMPURA-Qwen2.5-VL-3B-s1 +datasets: +- andaba/TEMPURA-VER +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/andaba/TEMPURA-Qwen2.5-VL-3B-s1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#TEMPURA-Qwen2.5-VL-3B-s1-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-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/TEMPURA-Qwen2.5-VL-3B-s1-GGUF/resolve/main/TEMPURA-Qwen2.5-VL-3B-s1.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-s1.IQ4_XS.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.IQ4_XS.gguf new file mode 100644 index 0000000..0f7cddb --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a14d21af9d794658720eeb190a5256eaaa271c82bb4fc32e6e332e4cc1b8cb +size 1753186016 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q2_K.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q2_K.gguf new file mode 100644 index 0000000..2e49f50 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f3c0206d02268f362f29744027c591c78b3abbe7dc603c2dd74c8290ab6428b +size 1274756832 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_L.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_L.gguf new file mode 100644 index 0000000..7b5b88b --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ec26e82a0e29bab0150e099c031f4c5886f032e6746b8eadde091d03e908ee0 +size 1707392736 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_M.gguf new file mode 100644 index 0000000..1511a72 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a99816920e9d61a756cc5f498f7250c6cf304ad1692384a152c035136990cb3 +size 1590476512 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_S.gguf new file mode 100644 index 0000000..cd3c021 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c239b35cb616fbfbe6f209a0a4145289e43ff742b0080e3f0745f7de2264eb +size 1454358240 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_M.gguf new file mode 100644 index 0000000..ee88bc4 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4abb78f888981912fd149c3e3fefbb72a183c0159c7f169d1022afefb4f6d59e +size 1929903840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_S.gguf new file mode 100644 index 0000000..b5eb46d --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85048dd7570a31ff577180ca0f0231a8927d465d6ca264e80360f2f3f7820f29 +size 1834385120 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_M.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_M.gguf new file mode 100644 index 0000000..2755c85 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c869ad5ad7333391118e5eed9c13a77aba08f3c8034b1ea556af28f53f3c439b +size 2224815840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_S.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_S.gguf new file mode 100644 index 0000000..1a46ce8 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1d20239d23bc6b03933769e43d973e24979bc6fb48aab30851f0352181ef80 +size 2169667296 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q6_K.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q6_K.gguf new file mode 100644 index 0000000..24c4c6a --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:366f921c0b673c7784b4a9cf6482dbed402165bb6ea1bb70c35167ebdb8c1edf +size 2538159840 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.Q8_0.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.Q8_0.gguf new file mode 100644 index 0000000..c6e4544 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb28a8cacdd990d455577408d7ab347c5132f1134041e5beb6518f2549d2c02d +size 3285477088 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.f16.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.f16.gguf new file mode 100644 index 0000000..1eaf6a4 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77676ea7ef57a2f5cbb5a1f6756e4c338f52b9d6440ef9ca14d6aa26b483b09b +size 6178318048 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-Q8_0.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-Q8_0.gguf new file mode 100644 index 0000000..467fdc6 --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2994f83e7e295ade79e796d034c20a7f5dcd8006fb32a88729a2559b9c62fdc2 +size 844758656 diff --git a/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-f16.gguf b/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-f16.gguf new file mode 100644 index 0000000..1e8043a --- /dev/null +++ b/TEMPURA-Qwen2.5-VL-3B-s1.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a647e9447f3e16fffa7ff2512ba220f3fbf08ba9a288c4c5153004808edc2036 +size 1338429056