commit 25343d56ecad8578eeceb3bbdcd3f714d9b4bfb2 Author: ModelHub XC Date: Mon Aug 17 22:51:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/s1-Qwen2.5-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0174803 --- /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 +s1-Qwen2.5-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +s1-Qwen2.5-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..73c3ab8 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: mothnaZl/s1-Qwen2.5-7B +language: +- en +library_name: transformers +model_name: s1-Qwen-Qwen2.5-7B-32768-20250310_194302 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/mothnaZl/s1-Qwen2.5-7B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/s1-Qwen2.5-7B-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/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/s1-Qwen2.5-7B-GGUF/resolve/main/s1-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. + + diff --git a/s1-Qwen2.5-7B.IQ4_XS.gguf b/s1-Qwen2.5-7B.IQ4_XS.gguf new file mode 100644 index 0000000..ae9767f --- /dev/null +++ b/s1-Qwen2.5-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32129b339114f174ab0ba1138516069acc4565df2e70e6787527df5f28915a27 +size 4250298976 diff --git a/s1-Qwen2.5-7B.Q2_K.gguf b/s1-Qwen2.5-7B.Q2_K.gguf new file mode 100644 index 0000000..e5e39f3 --- /dev/null +++ b/s1-Qwen2.5-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630eb43ab678319af9e5f8b72b4f7fb9f3b4f846cd8178c593eeaa92fb7e853e +size 3015940704 diff --git a/s1-Qwen2.5-7B.Q3_K_L.gguf b/s1-Qwen2.5-7B.Q3_K_L.gguf new file mode 100644 index 0000000..1801536 --- /dev/null +++ b/s1-Qwen2.5-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655c567f50541d3ab320ec3a631f6651387c5fd999690c3e4d8fc1357418382d +size 4088459872 diff --git a/s1-Qwen2.5-7B.Q3_K_M.gguf b/s1-Qwen2.5-7B.Q3_K_M.gguf new file mode 100644 index 0000000..1a3f307 --- /dev/null +++ b/s1-Qwen2.5-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74653ce14ca773c29cd48381740fc856280be23c3e76c7f68a1c09aa9e873c4 +size 3808391776 diff --git a/s1-Qwen2.5-7B.Q3_K_S.gguf b/s1-Qwen2.5-7B.Q3_K_S.gguf new file mode 100644 index 0000000..b28fa5d --- /dev/null +++ b/s1-Qwen2.5-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e79b0198bc68d71f506dd79de529e588e1b302b116cf2b03ebfbb5f19141abe +size 3492368992 diff --git a/s1-Qwen2.5-7B.Q4_K_M.gguf b/s1-Qwen2.5-7B.Q4_K_M.gguf new file mode 100644 index 0000000..3cd81a4 --- /dev/null +++ b/s1-Qwen2.5-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b1897c722399f148d269a7e6989634d0525b83ac6210713e328bd824135cc2a +size 4683074144 diff --git a/s1-Qwen2.5-7B.Q4_K_S.gguf b/s1-Qwen2.5-7B.Q4_K_S.gguf new file mode 100644 index 0000000..62c89c7 --- /dev/null +++ b/s1-Qwen2.5-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca77e75deaa538854c7368fabb54828f6369d272371c92e48fcc507754bdcf1b +size 4457769568 diff --git a/s1-Qwen2.5-7B.Q5_K_M.gguf b/s1-Qwen2.5-7B.Q5_K_M.gguf new file mode 100644 index 0000000..8101bf2 --- /dev/null +++ b/s1-Qwen2.5-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190948e915d09824c72edb244b8a8002a8f0cce2753eadf69391162354729681 +size 5444831840 diff --git a/s1-Qwen2.5-7B.Q5_K_S.gguf b/s1-Qwen2.5-7B.Q5_K_S.gguf new file mode 100644 index 0000000..66f5a9e --- /dev/null +++ b/s1-Qwen2.5-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c78f057d15c16820e7874927a35d4ca196290176827968945ecf7bfeea824aac +size 5315177056 diff --git a/s1-Qwen2.5-7B.Q6_K.gguf b/s1-Qwen2.5-7B.Q6_K.gguf new file mode 100644 index 0000000..ea67ed2 --- /dev/null +++ b/s1-Qwen2.5-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2d2abc5b8ba0d495f506e1114cd14f407fca2618afa493132a1fbca4b50951 +size 6254199392 diff --git a/s1-Qwen2.5-7B.Q8_0.gguf b/s1-Qwen2.5-7B.Q8_0.gguf new file mode 100644 index 0000000..0833245 --- /dev/null +++ b/s1-Qwen2.5-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d86b311fc06836e0f6f016a4fcd4fa05079af0ecf0689877f373e7697f2b26 +size 8098525792 diff --git a/s1-Qwen2.5-7B.f16.gguf b/s1-Qwen2.5-7B.f16.gguf new file mode 100644 index 0000000..64f6771 --- /dev/null +++ b/s1-Qwen2.5-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6d1ba31e4928e59c6d2d138d7236812506c04957538757573476270fa44c2d2 +size 15237853792