commit d062c7bec2fab429a34ad62a726fa98966981298 Author: ModelHub XC Date: Sat Jun 13 19:08:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MM-RAIT-Qwen2.5-VL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d1b69c4 --- /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 +MM-RAIT-Qwen2.5-VL.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.f16.gguf filter=lfs diff=lfs merge=lfs -text +MM-RAIT-Qwen2.5-VL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MM-RAIT-Qwen2.5-VL.IQ4_XS.gguf b/MM-RAIT-Qwen2.5-VL.IQ4_XS.gguf new file mode 100644 index 0000000..585c015 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37f79df42b7af75a0f5951dd45d0dc11ddd6c46f34e65e17cdea79bea2911d20 +size 4250297280 diff --git a/MM-RAIT-Qwen2.5-VL.Q2_K.gguf b/MM-RAIT-Qwen2.5-VL.Q2_K.gguf new file mode 100644 index 0000000..2214588 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ef39e9bbbd8bc47634a6d9e6b8b60966002d4e30954c7fa21abeba7df3a437c +size 3015939008 diff --git a/MM-RAIT-Qwen2.5-VL.Q3_K_L.gguf b/MM-RAIT-Qwen2.5-VL.Q3_K_L.gguf new file mode 100644 index 0000000..7a7dc6f --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ca1230fd0d11f8251239ab07dbcec0a76d68822f9709e85d44d4dd436153bd8 +size 4088458176 diff --git a/MM-RAIT-Qwen2.5-VL.Q3_K_M.gguf b/MM-RAIT-Qwen2.5-VL.Q3_K_M.gguf new file mode 100644 index 0000000..2888ee0 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b05d78c928b229fbc2528be264a6bbfd8ede4c0b25f57aa450d2e334b57a1e +size 3808390080 diff --git a/MM-RAIT-Qwen2.5-VL.Q3_K_S.gguf b/MM-RAIT-Qwen2.5-VL.Q3_K_S.gguf new file mode 100644 index 0000000..e2a45d5 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c35be90cefab85ad3e11c87114c61d29c6c10ecc06cdc9326f8bd0851086d3a0 +size 3492367296 diff --git a/MM-RAIT-Qwen2.5-VL.Q4_K_M.gguf b/MM-RAIT-Qwen2.5-VL.Q4_K_M.gguf new file mode 100644 index 0000000..45f43b6 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d65f5d1a77581a2ddf0ef1b1f60d3c3fd6408431c3ade8620f3869fd88baf126 +size 4683072448 diff --git a/MM-RAIT-Qwen2.5-VL.Q4_K_S.gguf b/MM-RAIT-Qwen2.5-VL.Q4_K_S.gguf new file mode 100644 index 0000000..edd9b40 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9709159a99f49a1bde42565f07e9da589f0587fac4fb80376a4b3fc73ae7e184 +size 4457767872 diff --git a/MM-RAIT-Qwen2.5-VL.Q5_K_M.gguf b/MM-RAIT-Qwen2.5-VL.Q5_K_M.gguf new file mode 100644 index 0000000..f6c60d4 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c561d9767060c9e552d0f0653b083cbf291ab241742418a0da04b8a69c1854 +size 5444830144 diff --git a/MM-RAIT-Qwen2.5-VL.Q5_K_S.gguf b/MM-RAIT-Qwen2.5-VL.Q5_K_S.gguf new file mode 100644 index 0000000..d156c9c --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da6e250d160bb8dd9f56485bf4632103ec221ad7ac4023d4cfc1f55e2d0c3b0 +size 5315175360 diff --git a/MM-RAIT-Qwen2.5-VL.Q6_K.gguf b/MM-RAIT-Qwen2.5-VL.Q6_K.gguf new file mode 100644 index 0000000..38fad83 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28cc5493fbc0da28bf50feb248041fdd22b9e7ebfd3562ddd0b7f8d64bc9c73f +size 6254197696 diff --git a/MM-RAIT-Qwen2.5-VL.Q8_0.gguf b/MM-RAIT-Qwen2.5-VL.Q8_0.gguf new file mode 100644 index 0000000..1ffc0eb --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a77f7179c68a087b39f51bd312edc48ab7ec147a156382ac8334be862b49a378 +size 8098524096 diff --git a/MM-RAIT-Qwen2.5-VL.f16.gguf b/MM-RAIT-Qwen2.5-VL.f16.gguf new file mode 100644 index 0000000..662e5f8 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eeb3976a8defaf1ad82d37d03bfa18dc1f2009fdc4ab4c8dddc762e2f1f2670 +size 15237852096 diff --git a/MM-RAIT-Qwen2.5-VL.mmproj-Q8_0.gguf b/MM-RAIT-Qwen2.5-VL.mmproj-Q8_0.gguf new file mode 100644 index 0000000..486638d --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f8c28bde8da3142c9824511f638d543103706c7c4c235229180f8fb4003d99 +size 853119648 diff --git a/MM-RAIT-Qwen2.5-VL.mmproj-f16.gguf b/MM-RAIT-Qwen2.5-VL.mmproj-f16.gguf new file mode 100644 index 0000000..5b02936 --- /dev/null +++ b/MM-RAIT-Qwen2.5-VL.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b72be112319f4990da258749e23f64a85ee6f3bd851599bcebc2caa36837803 +size 1354162848 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ced6405 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +arxiv: 2502.17297 +base_model: whalezzz/MM-RAIT-Qwen2.5-VL +datasets: +- whalezzz/M2RAG +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/whalezzz/MM-RAIT-Qwen2.5-VL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MM-RAIT-Qwen2.5-VL-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/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MM-RAIT-Qwen2.5-VL-GGUF/resolve/main/MM-RAIT-Qwen2.5-VL.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. + +