commit c2e32ca2f48172ed78039ba309bc65d880684346 Author: ModelHub XC Date: Thu Aug 6 05:53:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50e370d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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-light_Qwen2.5-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SAGE-light_Qwen2.5-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..05b60eb --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: baohao/SAGE-light_Qwen2.5-7B-Instruct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/baohao/SAGE-light_Qwen2.5-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SAGE-light_Qwen2.5-7B-Instruct-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/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SAGE-light_Qwen2.5-7B-Instruct-GGUF/resolve/main/SAGE-light_Qwen2.5-7B-Instruct.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-light_Qwen2.5-7B-Instruct.IQ4_XS.gguf b/SAGE-light_Qwen2.5-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..ce2fc87 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51967e8704bd108bf9c4c0abe7e9aae6f404aabdf0306d5f86ff9c03ef68a60e +size 4250298848 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q2_K.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..9caa0ba --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97941d57f3195c658e1d75988950a0e9f058aec24a8e2736d772c591e521a74d +size 3015940576 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_L.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..3216727 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa35b46d6223baf771e91eb37ef500a60636ae1559b2b0160ef43f2626c1d75e +size 4088459744 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_M.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..40c68e1 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b726cc27c28ca0e842577c76d232b08ba26712a1efa46b4fe2b0d90ed2875eab +size 3808391648 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_S.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..f17ef6e --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f0b49dd7d76d96fb9f33b4762022a04c75d9e3e20e344644273c35a18b87605 +size 3492368864 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_M.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..50e5997 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a491b7f8d91965853778d36eae23be4963c496bbf9d80b8580a5ba4653626789 +size 4683074016 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_S.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..4169310 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb00fce3f4f17d92221059955f561086e77db64a7eb507b98bd24eb92bd2a87a +size 4457769440 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_M.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..7a01310 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ff0e983802e928c851716ee1076a5791800542403b42571da1682e44765a693 +size 5444831712 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_S.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f495437 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ad6292e413d4f6d48285fae7b4e7fe088bfeddb9b7214d77960448d0e1b7373 +size 5315176928 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q6_K.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..36a5b4c --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42a20cdd801799e8e131f8b8e01d7e036c622dc4313c2d7f6a06d9ae1056744 +size 6254199264 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.Q8_0.gguf b/SAGE-light_Qwen2.5-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..96c7364 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea6e0c425eaa6987219b0b7c111d341b9fa54fff3d096e0ac463f407824f40b +size 8098525664 diff --git a/SAGE-light_Qwen2.5-7B-Instruct.f16.gguf b/SAGE-light_Qwen2.5-7B-Instruct.f16.gguf new file mode 100644 index 0000000..0a7c260 --- /dev/null +++ b/SAGE-light_Qwen2.5-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58113c0eba8f2cee9291fbf963d0b0ea5af061380e5d340da75a64c5816af3f2 +size 15237853664