commit 99cba4e7c178fb5936235615191523077934732f Author: ModelHub XC Date: Tue Jul 21 02:07:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..224318d --- /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 +Qwen2.5-Math-1.5B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Math-1.5B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Math-1.5B-SFT.IQ4_XS.gguf b/Qwen2.5-Math-1.5B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..b02572d --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2742c397b7699390e7cff91c47882cd6eafe7bed375684cb1c3847c76db12154 +size 902182848 diff --git a/Qwen2.5-Math-1.5B-SFT.Q2_K.gguf b/Qwen2.5-Math-1.5B-SFT.Q2_K.gguf new file mode 100644 index 0000000..14ff56e --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72e9defa3f2aaec58259eaf1e54654b5f18727ac14d73ca7a12b0aebef422f39 +size 676304832 diff --git a/Qwen2.5-Math-1.5B-SFT.Q3_K_L.gguf b/Qwen2.5-Math-1.5B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..68ecdb0 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c83a967ec3bff86244a0038218de8bfa3f06588be5e9e71882699fd04253ac35 +size 880162752 diff --git a/Qwen2.5-Math-1.5B-SFT.Q3_K_M.gguf b/Qwen2.5-Math-1.5B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..b424027 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f7a193e460dbee8371dedc057669a015d2d7d01eaa671d9a11124e9e177e270 +size 824178624 diff --git a/Qwen2.5-Math-1.5B-SFT.Q3_K_S.gguf b/Qwen2.5-Math-1.5B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..c532bc8 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d522e7112b252943d341a455154929f45492ad83cc5c9d887d16d01c3d7be72 +size 760944576 diff --git a/Qwen2.5-Math-1.5B-SFT.Q4_K_M.gguf b/Qwen2.5-Math-1.5B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..8bef5f9 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683d9a145efc994956ea43067cbbc4cc0bb7fe39d7f51039811348cb5a9fff82 +size 986048448 diff --git a/Qwen2.5-Math-1.5B-SFT.Q4_K_S.gguf b/Qwen2.5-Math-1.5B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..67565e0 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698f3ca43faebdf7a980f0259b6e51f8fd7df9c4ea943bad5ee0a14a89bfa69d +size 940312512 diff --git a/Qwen2.5-Math-1.5B-SFT.Q5_K_M.gguf b/Qwen2.5-Math-1.5B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..bb6f9ad --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72db67b139c3b35c61effb9af50218e9bb2c86711505525e7b05478c4956cda +size 1125050304 diff --git a/Qwen2.5-Math-1.5B-SFT.Q5_K_S.gguf b/Qwen2.5-Math-1.5B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..38a7250 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7be5c82dc39d94461c9e2a15922c9f5e43e270d63fe8ef984fdfaf0ab29d6a5 +size 1098729408 diff --git a/Qwen2.5-Math-1.5B-SFT.Q6_K.gguf b/Qwen2.5-Math-1.5B-SFT.Q6_K.gguf new file mode 100644 index 0000000..c9ea3b5 --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53d0dd60ef10e9801ce1df2703fc7bcf258d7eb3500bc09c4ce3163e419f10e6 +size 1272739776 diff --git a/Qwen2.5-Math-1.5B-SFT.Q8_0.gguf b/Qwen2.5-Math-1.5B-SFT.Q8_0.gguf new file mode 100644 index 0000000..ae3b88d --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1ee1bef07fccfcacc058b4aec1c1578a0aecdf4898c20c727c64fe97c2bdb6 +size 1646572992 diff --git a/Qwen2.5-Math-1.5B-SFT.f16.gguf b/Qwen2.5-Math-1.5B-SFT.f16.gguf new file mode 100644 index 0000000..ce14d0f --- /dev/null +++ b/Qwen2.5-Math-1.5B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2123116cd7ac81a02605d5567b804b47933a8c64f1655023ce4e62a1db9b8384 +size 3093669312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c1a6f04 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: jwhj/Qwen2.5-Math-1.5B-SFT +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jwhj/Qwen2.5-Math-1.5B-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Math-1.5B-SFT-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/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Math-1.5B-SFT-GGUF/resolve/main/Qwen2.5-Math-1.5B-SFT.f16.gguf) | f16 | 3.2 | 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. + +