commit 34057a017e149014be90f5e3e19a4959bbe6dc6f Author: ModelHub XC Date: Mon Jun 15 22:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c4225c --- /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-7B-GRPO_Math.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.IQ4_XS.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.IQ4_XS.gguf new file mode 100644 index 0000000..05e8953 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87f52465b32491defad70984da575b5d9f11486ee6661e50c033dcabc377fdc +size 4250299296 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q2_K.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q2_K.gguf new file mode 100644 index 0000000..aef6946 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4b19250d7c6c797e1d297a61c35e8b21676bc4a0a817308ef30315af716728 +size 3015941024 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_L.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_L.gguf new file mode 100644 index 0000000..a3c8ba0 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7264cc16df43631b73d7767148b2f2b7be8f4bb97d22e0f04745e9669f4457a8 +size 4088460192 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_M.gguf new file mode 100644 index 0000000..ae56443 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c74a6c00d237bec02ef8c889660a599fb472c6040aa11bb3414d61125fc04b +size 3808392096 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_S.gguf new file mode 100644 index 0000000..bb7ac87 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f8e0101ab327be9cd6525cc702224893ed396981f3284d42535bed93c2b69e +size 3492369312 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_M.gguf new file mode 100644 index 0000000..2851114 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a182ee8616f4913bf2430ef5dd96aa9592761290ae76b852588f72e7882a88bc +size 4683074464 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_S.gguf new file mode 100644 index 0000000..3e8f033 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349e8c99a1f9831c3dbc2b208f032f0b4342709866dc258d1b88e7907c438573 +size 4457769888 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_M.gguf new file mode 100644 index 0000000..2ba630c --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b7ab34669aefb9180d54f2ab88eb97aa9d5cfdc355d598348e0d1164b462398 +size 5444832160 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_S.gguf new file mode 100644 index 0000000..a3d9ef3 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb524ac615317e789d3184a92e23b5237012d5861438b77b3a7d3c0e1a79d98 +size 5315177376 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q6_K.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q6_K.gguf new file mode 100644 index 0000000..7116beb --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a59df8d17260c99a1264744f5ca4a5f6acecd8af80196c08117f157bc86cda +size 6254199712 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q8_0.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q8_0.gguf new file mode 100644 index 0000000..7be3190 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83194cc007963d068fbdcea15202663c8b7f7e8d0630d5bf1f94d4716d784dd2 +size 8098526112 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.f16.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.f16.gguf new file mode 100644 index 0000000..ad44482 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c23d41abdd079f36e27ff7b94673655c44635de2e1a21666c1baff768ec271d +size 15237854112 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c167093 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Qwen-7B-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-7B-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-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO_Math.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. + +