commit 6ca68d52ac0b75eeac648d7722d25aa5402ff13e Author: ModelHub XC Date: Thu Jun 11 23:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0cfbb98 --- /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 +KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KAIROS-MM-Qwen2.5-VL-7B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.IQ4_XS.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..89efec6 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be73766122dcd7007918d4f394e28150c1de83573ec8c40cd0331a2a5819ad56 +size 4250298496 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q2_K.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q2_K.gguf new file mode 100644 index 0000000..21ee898 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9748e01719528b32be1461d91b93bb2e0121d9776328ade1b613625871011c3 +size 3015940224 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_L.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..c9a6028 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8702e0025f5cea4b8d359ac96397a70f691a7ec5c5136363e96d2c03f3c8c2cd +size 4088459392 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..ccf758c --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3519fac575b9e8628cc1a78be2f03e74f4630c44b62611e615fbbc9fd931b56 +size 3808391296 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..646a358 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23eac1d144aa1006788fd060bb908b512e255508fdc88fa6e3d65cdc6986e68 +size 3492368512 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..8d0becc --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb01ba80370f2922b3e3368ccd9a685ac9361ad7f24102ec26b051abaf3eafc2 +size 4683073664 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..784c870 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99355548ac463466530c774b8ec38cc8ec6338cc1e6d1fc76c12adc8a103e02 +size 4457769088 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_M.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..4818672 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecfb50782c8c9d1bed756ccae79843f422a8b703c57bee3b9fc16bf75afce95e +size 5444831360 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_S.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..cc86a3f --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e42ad25d46a1e2d8330166b23dbb87380f4c6a83f3f152ceef2af579532ab8 +size 5315176576 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q6_K.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q6_K.gguf new file mode 100644 index 0000000..fb657fd --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151214e144168d65280907dc49ffec4caf641d97f86e455816aa56969c074c39 +size 6254198912 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q8_0.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q8_0.gguf new file mode 100644 index 0000000..2131934 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42de3725b760f6c7d4cd2986f272c363eda9b9475a99a7221740522893dac872 +size 8098525312 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.f16.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.f16.gguf new file mode 100644 index 0000000..3ed784f --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ce0f823b234086ceff4a376ea7f066fa081543cf647de8ad36ad90e11c7581 +size 15237853312 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-Q8_0.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-Q8_0.gguf new file mode 100644 index 0000000..4ab1151 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1525d9ee37b9225afa40fb38c3e3431de468714efea60d8fb5e0cec068cf9fb5 +size 856131424 diff --git a/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-f16.gguf b/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-f16.gguf new file mode 100644 index 0000000..d66c963 --- /dev/null +++ b/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09400dc31504098827915a160ea2f6c528fcd417e65fa5eac09bf00dd42ede29 +size 1354164064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1019ef0 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT +datasets: +- allenai/SAGE-MM-SFT-417K +- nvidia/Cosmos-Reason1-SFT-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- video-reasoning +- text-generation-inference +- pytorch +- agent +- reasoning +- long-horizon-reasoning +- temporal-reasoning +- spatial-reasoning +- physical-reasoning +- common-sense-reasoning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/prithivMLmods/KAIROS-MM-Qwen2.5-VL-7B-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-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/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KAIROS-MM-Qwen2.5-VL-7B-SFT-GGUF/resolve/main/KAIROS-MM-Qwen2.5-VL-7B-SFT.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. + +