commit 7c517f2d73613c7745a6917e7213725f992d6971 Author: ModelHub XC Date: Sun Oct 11 03:42:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6ae471 --- /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 +DeepSeekMath-Base-SFT-Step-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeekMath-Base-SFT-Step-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeekMath-Base-SFT-Step-DPO.IQ4_XS.gguf b/DeepSeekMath-Base-SFT-Step-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..88200d9 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e495eec63d1d27dff9cd19e941811ec6224a046ebd269fec99a429f7bba51813 +size 3805037664 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q2_K.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q2_K.gguf new file mode 100644 index 0000000..ac481aa --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6497f91065a1a68bf827e05121c3bd83fe82ef793a04a2ce4732e960f8ef311f +size 2707092128 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_L.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..c138177 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de20f3ff8fcbc8e3bc5388aed7e25ac358cbea468f1896007ba16c807b9d619b +size 3733945216 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_M.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..5d65d7e --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a818fa853ebfeb9ef4f3a65b001f45a03819e118c872008b01968193f44d51 +size 3448863616 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_S.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..ea7ba21 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f583a6661070bdbc7d20071c21c3cabbf73d0024affc10f65eff4d5970b54483 +size 3125689216 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_M.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..c5ebf00 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fea02c60c6f19583d7f1beca1a5567641f0f61ebe681e8ad2e6ad7199933ff +size 4209726944 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_S.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..3525c92 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc9b71d28fbc7124b3ccc362756d15b13bdfda74524c62fcdf3aab74ffc796b1 +size 4011726304 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_M.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..500f684 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce652a0f5c0ad8eb145195b6598a26fe871c51e475b7239c94fee7769a86951a +size 4911569888 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_S.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..f1bfedd --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d62f421849ce3e7897dbe1dcb8f78143897522bc6a4711d2d0d3489e73cc6bd5 +size 4796537824 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q6_K.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q6_K.gguf new file mode 100644 index 0000000..914372f --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ceb53b80e96902670d926d608ff849793b9824dc0238513c0ada82993f7570 +size 5657278016 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.Q8_0.gguf b/DeepSeekMath-Base-SFT-Step-DPO.Q8_0.gguf new file mode 100644 index 0000000..2bd19ea --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:577609fee4a64844b143b0ba601b4fdffac1c66a7b351737da07d6ec70440a4b +size 7326066048 diff --git a/DeepSeekMath-Base-SFT-Step-DPO.f16.gguf b/DeepSeekMath-Base-SFT-Step-DPO.f16.gguf new file mode 100644 index 0000000..a045558 --- /dev/null +++ b/DeepSeekMath-Base-SFT-Step-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befed8a2e0f185f1fe70fb7a333d6eca050a806060224516e18686dc8ffd72a2 +size 13785890688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bfda8dd --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: xinlai/DeepSeekMath-Base-SFT-Step-DPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/xinlai/DeepSeekMath-Base-SFT-Step-DPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DeepSeekMath-Base-SFT-Step-DPO-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/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_S.gguf) | Q3_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_M.gguf) | Q3_K_M | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q3_K_L.gguf) | Q3_K_L | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.Q8_0.gguf) | Q8_0 | 7.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeekMath-Base-SFT-Step-DPO-GGUF/resolve/main/DeepSeekMath-Base-SFT-Step-DPO.f16.gguf) | f16 | 13.9 | 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. + +