commit 756893a69996fe490fcd84584e2ad83e6847b7a4 Author: ModelHub XC Date: Mon Aug 10 14:27:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GoG-SFT-Qwen2.5-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4599e8e --- /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 +GoG-SFT-Qwen2.5-7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GoG-SFT-Qwen2.5-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GoG-SFT-Qwen2.5-7B.IQ4_XS.gguf b/GoG-SFT-Qwen2.5-7B.IQ4_XS.gguf new file mode 100644 index 0000000..b6edb88 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f62b74d967b5d78e77319b18ebcabe023df4d4db9d3f199cd792f0c6f77d3ba +size 4250297312 diff --git a/GoG-SFT-Qwen2.5-7B.Q2_K.gguf b/GoG-SFT-Qwen2.5-7B.Q2_K.gguf new file mode 100644 index 0000000..783db14 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecaf6de116c3c0c7ec4a84079b112f108b66c60b7954e659b1a605457c757705 +size 3015939040 diff --git a/GoG-SFT-Qwen2.5-7B.Q3_K_L.gguf b/GoG-SFT-Qwen2.5-7B.Q3_K_L.gguf new file mode 100644 index 0000000..2e968d4 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0268240d57d806e473b822872b72a10f7e4f235160441b91e341ed34322d5eb6 +size 4088458208 diff --git a/GoG-SFT-Qwen2.5-7B.Q3_K_M.gguf b/GoG-SFT-Qwen2.5-7B.Q3_K_M.gguf new file mode 100644 index 0000000..5d588f7 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfebd002e4224981fca63043d8c12bc0777e0ebb0987f8a09342e0951998e4e4 +size 3808390112 diff --git a/GoG-SFT-Qwen2.5-7B.Q3_K_S.gguf b/GoG-SFT-Qwen2.5-7B.Q3_K_S.gguf new file mode 100644 index 0000000..d0c7325 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cc14085e7760335c83f4b796697270931986bb665fdb9c58635d3e5489ccd1 +size 3492367328 diff --git a/GoG-SFT-Qwen2.5-7B.Q4_K_M.gguf b/GoG-SFT-Qwen2.5-7B.Q4_K_M.gguf new file mode 100644 index 0000000..e14acbb --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e4a4907a36017149e0576290f930c64e9f3aef879fde23017771f38112b51c7 +size 4683072480 diff --git a/GoG-SFT-Qwen2.5-7B.Q4_K_S.gguf b/GoG-SFT-Qwen2.5-7B.Q4_K_S.gguf new file mode 100644 index 0000000..696cbaf --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbdef4736079f78687873d17f905a8d2e7c3494fbf13cd724330592b96ce248 +size 4457767904 diff --git a/GoG-SFT-Qwen2.5-7B.Q5_K_M.gguf b/GoG-SFT-Qwen2.5-7B.Q5_K_M.gguf new file mode 100644 index 0000000..38fec2e --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34047e43999406a17ac34e6525d3580cf13720db930faffc22a07b50f2694ef5 +size 5444830176 diff --git a/GoG-SFT-Qwen2.5-7B.Q5_K_S.gguf b/GoG-SFT-Qwen2.5-7B.Q5_K_S.gguf new file mode 100644 index 0000000..a0e8c61 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:873becc52367cc9abf11cf52ee5d847760b818fd88af7ddd2670382ecca99e28 +size 5315175392 diff --git a/GoG-SFT-Qwen2.5-7B.Q6_K.gguf b/GoG-SFT-Qwen2.5-7B.Q6_K.gguf new file mode 100644 index 0000000..f72bdd4 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88b6744a37052629d01e79458d68f89742cfb42d60957943f1cf735cc7047ea +size 6254197728 diff --git a/GoG-SFT-Qwen2.5-7B.Q8_0.gguf b/GoG-SFT-Qwen2.5-7B.Q8_0.gguf new file mode 100644 index 0000000..53d5b03 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc55309d61c0e2d1611023f10dc1224b1f563b6be8740d161de01cc1739869b +size 8098524128 diff --git a/GoG-SFT-Qwen2.5-7B.f16.gguf b/GoG-SFT-Qwen2.5-7B.f16.gguf new file mode 100644 index 0000000..63172f1 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:467b6f7b58b3e556cceb480800a65ee92b4f3dfb3569963afa5581fb8242fbce +size 15237852128 diff --git a/GoG-SFT-Qwen2.5-7B.mmproj-Q8_0.gguf b/GoG-SFT-Qwen2.5-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..93b3cdc --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0319f49acbfe46c4e21f98e5ef2d5e3536dbfd66006accd1a7ce5524c2601cf9 +size 856130304 diff --git a/GoG-SFT-Qwen2.5-7B.mmproj-f16.gguf b/GoG-SFT-Qwen2.5-7B.mmproj-f16.gguf new file mode 100644 index 0000000..c14d9a2 --- /dev/null +++ b/GoG-SFT-Qwen2.5-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f1acb8c229257835ed3c83bc9d6e353a8d7f02ca4db6b4abafc7a389b799411 +size 1354162944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6c7be2f --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: Edwinzz/GoG-SFT-Qwen2.5-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Edwinzz/GoG-SFT-Qwen2.5-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GoG-SFT-Qwen2.5-7B-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/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GoG-SFT-Qwen2.5-7B-GGUF/resolve/main/GoG-SFT-Qwen2.5-7B.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. + +