commit b2aae349807a59fdb48d058a8ec1502efec71103 Author: ModelHub XC Date: Fri May 1 09:37:13 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-8B-Suanming-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..608aeb2 --- /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 +DeepSeek-R1-8B-Suanming.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-8B-Suanming.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-8B-Suanming.IQ4_XS.gguf b/DeepSeek-R1-8B-Suanming.IQ4_XS.gguf new file mode 100644 index 0000000..4fdb3ce --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f318403ee295afbcdf3445fcbc681045ea224fc0cca1d479dc96d92568140f +size 4484366112 diff --git a/DeepSeek-R1-8B-Suanming.Q2_K.gguf b/DeepSeek-R1-8B-Suanming.Q2_K.gguf new file mode 100644 index 0000000..e5627aa --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06138570cf047d15e426ce9edc0f9319c4c0cec5875de1cd8f28a5d952a03076 +size 3179134752 diff --git a/DeepSeek-R1-8B-Suanming.Q3_K_L.gguf b/DeepSeek-R1-8B-Suanming.Q3_K_L.gguf new file mode 100644 index 0000000..4b724be --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b13af3dee0e4194dcf378d932eb12653bb0b3d97beff1d4cb27d098410ca354 +size 4321959712 diff --git a/DeepSeek-R1-8B-Suanming.Q3_K_M.gguf b/DeepSeek-R1-8B-Suanming.Q3_K_M.gguf new file mode 100644 index 0000000..da4d42c --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6d616cecd9a7dc752f114597450fa1b3603fcfc3bf33b858d1ec4da1612ed8a +size 4018921248 diff --git a/DeepSeek-R1-8B-Suanming.Q3_K_S.gguf b/DeepSeek-R1-8B-Suanming.Q3_K_S.gguf new file mode 100644 index 0000000..5808643 --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cfa622b4ad87a92ab9d7a22e2f1c7f5b72f9b3b17a24d2ef24f1467459df33d +size 3664502560 diff --git a/DeepSeek-R1-8B-Suanming.Q4_K_M.gguf b/DeepSeek-R1-8B-Suanming.Q4_K_M.gguf new file mode 100644 index 0000000..fbb7da4 --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c382cb22c34865e17a8cf2d4113271edd8a7e6274a7b11f0bf0e3fced90607d3 +size 4920737568 diff --git a/DeepSeek-R1-8B-Suanming.Q4_K_S.gguf b/DeepSeek-R1-8B-Suanming.Q4_K_S.gguf new file mode 100644 index 0000000..6a34a8c --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d78dcb114ae5693ca71251817657c7816b7da88db37712530437bd49ebcfba +size 4692672288 diff --git a/DeepSeek-R1-8B-Suanming.Q5_K_M.gguf b/DeepSeek-R1-8B-Suanming.Q5_K_M.gguf new file mode 100644 index 0000000..6ebf454 --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ba647e293c0097cce0b881e3ca6788651878b9bfa97663b38c2ad2dc08da675 +size 5732990752 diff --git a/DeepSeek-R1-8B-Suanming.Q5_K_S.gguf b/DeepSeek-R1-8B-Suanming.Q5_K_S.gguf new file mode 100644 index 0000000..ef00f52 --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8688384d8ef2d62e4b3564d6a611e1fc9dbf18c1375a6fc99f7bb56998d7ad +size 5599297312 diff --git a/DeepSeek-R1-8B-Suanming.Q6_K.gguf b/DeepSeek-R1-8B-Suanming.Q6_K.gguf new file mode 100644 index 0000000..e31b84c --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a397061076164bfce0719ba35746847186f27775637612a97c734ffe5dce3b35 +size 6596009760 diff --git a/DeepSeek-R1-8B-Suanming.Q8_0.gguf b/DeepSeek-R1-8B-Suanming.Q8_0.gguf new file mode 100644 index 0000000..88151bf --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7224b5736056741176b095d67e31d8bca8a20fb58e5f18f318488fc95dfd1f3f +size 8540774176 diff --git a/DeepSeek-R1-8B-Suanming.f16.gguf b/DeepSeek-R1-8B-Suanming.f16.gguf new file mode 100644 index 0000000..d11e106 --- /dev/null +++ b/DeepSeek-R1-8B-Suanming.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c7734701fbed2731a3321f49614eb8f02cbec0118ca8e87fd944fc95b644ff +size 16068894496 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3059dc5 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: santwilliam/DeepSeek-R1-8B-Suanming +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/santwilliam/DeepSeek-R1-8B-Suanming + + +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/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-8B-Suanming-GGUF/resolve/main/DeepSeek-R1-8B-Suanming.f16.gguf) | f16 | 16.2 | 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. + +