commit a12ba9bff428bd195b5ace2aa3fd601e94f3101c Author: ModelHub XC Date: Wed May 27 18:59:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bab8cb3 --- /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.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-7B-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.IQ4_XS.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..16a6f63 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259110f5d5565a39cbe511216f627afda20f527f313ed9aba6d441aa2cd23a76 +size 4250299264 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q2_K.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q2_K.gguf new file mode 100644 index 0000000..84f7119 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4410e8ebf07416cfb19fa0257f9196e32fb11d850fa10ed7f949e11be8fb31 +size 3015940992 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_L.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..5b55279 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49521d7595524157c7d897b50b57db91315b1f74f150adafd9f41c527114abf2 +size 4088460160 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..36adb5e --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce5a7be68c66c235ca0eb39dffd7bd055088e21c4a5e84e58fcc79c93bb5965 +size 3808392064 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..ab3034a --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a689c8e5f92e473aed5c221d56caa3e92f2df538e643dcfbcb4975fa6e0705 +size 3492369280 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..cdaae99 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ba678e8ef268d7f1a5d65331e6ae63a5595476aac8e5d87d0ceb730a00563d +size 4683074432 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..68c7e25 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4535df7f1de31c73a66bce710519a92cb8282c210192b4c65e166e0e467b69f5 +size 4457769856 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_M.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..22420e4 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f46725e6dc6ed73b55aa01ab26bb1da9de7bea8ce6f9e7d637868818d405614 +size 5444832128 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_S.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..b48e453 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:055acfad1ab48c332fa0f30230c3f35cd2a0efdce0897eb6a0de27917f675c91 +size 5315177344 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q6_K.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q6_K.gguf new file mode 100644 index 0000000..6f70c17 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36db15d7af64a6778e0a11ff9ad242840f002620a81cb9dbdfa0ce11213b7659 +size 6254199680 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q8_0.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q8_0.gguf new file mode 100644 index 0000000..c2ea312 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99bedb1a73d841d4ea9d5fe73c6530d6de6d3e5d6c4a1cd8b36cede7683a7ea7 +size 8098526080 diff --git a/DeepSeek-R1-Distill-Qwen-7B-GRPO.f16.gguf b/DeepSeek-R1-Distill-Qwen-7B-GRPO.f16.gguf new file mode 100644 index 0000000..9a3b9b7 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-7B-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59299d9fd1dbc5f118084ed0b9c9d9d15afd31690798ca566a8a86b7deef91fb +size 15237854080 diff --git a/README.md b/README.md new file mode 100644 index 0000000..85df865 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Dongwei/DeepSeek-R1-Distill-Qwen-7B-GRPO +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Qwen-7B-GRPO +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 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-i1-GGUF +## 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-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-7B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-7B-GRPO.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. + +