commit d971c2a60737dae1f30c077a6e803f0ee9cedef2 Author: ModelHub XC Date: Fri Jul 10 08:21:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..942bb76 --- /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-Distill-Qwen-1.5B-GRPO_Math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.IQ4_XS.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.IQ4_XS.gguf new file mode 100644 index 0000000..cc5f6f3 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b3f3911e34011a3823e8cc4067a94ae93183b2d32ec2dd6772f6da2accb8ab2 +size 1026163232 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q2_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q2_K.gguf new file mode 100644 index 0000000..9c0572c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ddfbe7b168cdfd4b6c19a4222886a026cd13579f7598e7594661b71a5627ef +size 752881184 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_L.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_L.gguf new file mode 100644 index 0000000..3105578 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b2a5b1ba901560df5004e7e344503912fd41777eb69bfc295a129792f62e1a +size 980441120 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_M.gguf new file mode 100644 index 0000000..78bfb92 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9cda212c21714aa3481bdd25984e582fc66dacc13638aa9dc7e6d02e4916861 +size 924456992 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_S.gguf new file mode 100644 index 0000000..cae8208 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac790fc348a9717eb70e233d69a10ce20478cf64d5b1ff3c57648de23368d576 +size 861222944 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_M.gguf new file mode 100644 index 0000000..5a8f616 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7174b47c820fa748101cad48a94906117d945f4fac3321f2e3847f594b2681e7 +size 1117321760 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_S.gguf new file mode 100644 index 0000000..2013bc0 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6292808d4651c606e2312fc7e1b8796c7598a5445abaa66625887738b9339e09 +size 1071585824 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_M.gguf new file mode 100644 index 0000000..a2ee482 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c9c87fae93761989b6bc153a316804d0610431cb32db86ca4ddd9e2edcfb9d +size 1285495328 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_S.gguf new file mode 100644 index 0000000..19623d0 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2651b853faad2bf1468d54ce4ca674fbe062ba3a4ea0233082ad4bb70416a506 +size 1259174432 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q6_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q6_K.gguf new file mode 100644 index 0000000..d1093d1 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da2781b8f419c397691ec5777dfdf030ad688e4dcad7e2def85d7b6bf9123cc0 +size 1464179744 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q8_0.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q8_0.gguf new file mode 100644 index 0000000..c006dcf --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83cbd9c52b22fc0f4c8746bb1b54cccbe0e54f8fe99b21b77a6b7b3f169e2172 +size 1894533152 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.f16.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.f16.gguf new file mode 100644 index 0000000..4aa7c2c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20b5a69b67101a823213c0309ddf51c07abb7939a08049f9466e64987976e5a9 +size 3560417312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cf21ed4 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Dongwei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/Dongwei/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math + + +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-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO_Math.f16.gguf) | f16 | 3.7 | 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. + +