commit 3b82f63e5d4b83e75815c9f4574e6aee38f7a33c Author: ModelHub XC Date: Sat Jun 27 21:55:19 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-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0938dec --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepSeek-R1-Distill-Qwen-1.5B-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.IQ4_XS.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..51b8987 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236383cd8d93956e74205e78e55b2f7d7a9117711de60f7b282c4baf720b87ea +size 1026162944 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q2_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q2_K.gguf new file mode 100644 index 0000000..4392b30 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f59012d9cd0151a14eb69c83a7d4bb3ccfbf565088a2feb8649c937524f0ef +size 752880896 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_L.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..2e3cd2a --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c579e94ee003ab24a106e93466510b026798e9a49d378ca7c0a04b6860888222 +size 980440832 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..0a7d32b --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4167219357ebc6e3ed858a82933f5b85561e6dd65989d4349c38a56bcf816510 +size 924456704 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..8600c64 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8cd254eae3c8528b6b8cc4e0cd0f29be0ba819efb4c644527c57040079b88ed +size 861222656 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..e56c2b0 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d152f6277c6b4c8c79d769aae97413175a3faa797a3d3689805dc13a0aaeb433 +size 1117321472 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..d9051b1 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0881ef5896553dafc737f1fabb594ec7235a7f16168fb748319ca442bae5aea0 +size 1071585536 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_M.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..9b9c6f1 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90dc95ab343415e7c43dd18e8c0cd47edef7eec466191d3dc1ae81307c35728b +size 1285495040 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_S.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..f7c7d11 --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2ee9cca5de2d6437500ac79bad897b862d6b29a4365c83a58dbf768c97d779b +size 1259174144 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q6_K.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q6_K.gguf new file mode 100644 index 0000000..9b8207e --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b41d44cc27c11a4b37d09ab2397eff8e0644601b9db7d517c099da048eea95 +size 1464179456 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q8_0.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q8_0.gguf new file mode 100644 index 0000000..420232e --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbdbb2f2aa910a02ca23fafadd01cea243b1e7f7261e82f62ed7c3e9bb764f7 +size 1894532864 diff --git a/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.f16.gguf b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.f16.gguf new file mode 100644 index 0000000..12d824a --- /dev/null +++ b/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da100976c8da467c3badf5c0b6e29d78f562cb5a476be7af12016db1968d18cb +size 3560417024 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11fe25c --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: QYWH/DeepSeek-R1-Distill-Qwen-1.5B-GRPO +language: +- en +library_name: transformers +model_name: DeepSeek-R1-Distill-Qwen-1.5B-GRPO +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/QYWH/DeepSeek-R1-Distill-Qwen-1.5B-GRPO + + +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-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepSeek-R1-Distill-Qwen-1.5B-GRPO-GGUF/resolve/main/DeepSeek-R1-Distill-Qwen-1.5B-GRPO.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. + +