commit 3978418e1dfeb1e9edd9265dadd9a71088c0a389 Author: ModelHub XC Date: Thu Apr 30 18:43:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1df2c34 --- /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 +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.f16.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-MM-Qwen2.5-VL-7B-SFT_RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f390d96 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: allenai/SAGE-MM-Qwen2.5-VL-7B-SFT_RL +datasets: +- allenai/SAGE-MM-RL-7k +- allenai/SAGE-MM-SFT-417K +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/allenai/SAGE-MM-Qwen2.5-VL-7B-SFT_RL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-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/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-MM-Qwen2.5-VL-7B-SFT_RL-GGUF/resolve/main/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.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. + + diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.IQ4_XS.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.IQ4_XS.gguf new file mode 100644 index 0000000..586fa97 --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d43cfa925331ba0e9baf94b6618f1e8a62c6359e2799d626e10593234b5e67 +size 4250298272 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q2_K.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q2_K.gguf new file mode 100644 index 0000000..18e841b --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2472184d9ce36c9c4523b93e0812fc1242ea43d4fd03060e212550ace6b7de5a +size 3015940000 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_L.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_L.gguf new file mode 100644 index 0000000..456999a --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f0f1da38f8285facda47619844b890b81e43bbbbc877d98d2981bd164ace2f0 +size 4088459168 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_M.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_M.gguf new file mode 100644 index 0000000..448b851 --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a216cd723e95c794f1668c8875d2754ad9754385a36c7f019129317cb403990 +size 3808391072 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_S.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_S.gguf new file mode 100644 index 0000000..ebc6c00 --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a135f8765da031bda0f6f0c6ceb357babb6c227f9fbfad170decd43b30399828 +size 3492368288 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_M.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_M.gguf new file mode 100644 index 0000000..4ab97ed --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69d2b61e423d9eb19d9e0ed69254144077dfbdb7d26552a5bb8edf434015754 +size 4683073440 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_S.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_S.gguf new file mode 100644 index 0000000..7a2cfec --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f33823bbb5deb1b4ca063bd2a487c99866b47b4e376197dff93cb3afdab1e7 +size 4457768864 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_M.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_M.gguf new file mode 100644 index 0000000..4713718 --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f861da41a745bf9ce99d646ec0644441b01e3648fa7b5a6a969b53ef1776b9d2 +size 5444831136 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_S.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_S.gguf new file mode 100644 index 0000000..8d0368a --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67c61c460ddef36153456b8e85d196071c05fe5066c90f128df1c609fb033d59 +size 5315176352 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q6_K.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q6_K.gguf new file mode 100644 index 0000000..4765cea --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0513aebdb8d7fc180e42f2cad30ce7105e212c5768a5bc0896ef043f1b5ee6a8 +size 6254198688 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q8_0.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q8_0.gguf new file mode 100644 index 0000000..8986f81 --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44283b0ec6c505a29726dfd49924d0d77c1144f9b2df3ac31d6571e04c47c77 +size 8098525088 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.f16.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.f16.gguf new file mode 100644 index 0000000..f8186ac --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a4f149c4473580bf65e12231777b8eb116a75b7ce4bd7ca9819fa789eb1ef4 +size 15237853088 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-Q8_0.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-Q8_0.gguf new file mode 100644 index 0000000..35fb10e --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f398180304be8775ee75ad41552ef5ee2914312a80c98a50d8bffdd79ae3c4 +size 856131200 diff --git a/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-f16.gguf b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-f16.gguf new file mode 100644 index 0000000..70300af --- /dev/null +++ b/SAGE-MM-Qwen2.5-VL-7B-SFT_RL.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddbd7faa8938d2851998f1d1ff1fa2079e0c23ff27e4bac7bf2af7239727adeb +size 1354163840