commit 20c2e4cee3aecb3be6e29d6bcadaf2ebf5d709cc Author: ModelHub XC Date: Sun May 31 08:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bee1021 --- /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 +Qwen2.5-7B-Open-R1-Code-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Open-R1-Code-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.IQ4_XS.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..fd98438 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa63ffaa6fd55840a3f6e841de28f5159e77e7444dc0cff0ccbd96137a9232f7 +size 4250296864 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q2_K.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q2_K.gguf new file mode 100644 index 0000000..8f0c6ec --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a333cb12d4a3501b7fc99fbd6be4c25751ca28f17684b391f8f972c41d76ec2 +size 3015938592 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_L.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..32465f7 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08afc35822dd3c05f5fb985c78a9c59020ad7c794ff9d1addd46cbd3339f8ca6 +size 4088457760 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_M.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..ab31c3b --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bae0bb3958babdfc2197af1a43b8015731ffe71d6838d7af8162eb9a3b03586 +size 3808389664 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_S.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..8768fcb --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fce518076f6dc9c176f522b705881f12ac0b291562c78b570336b964e7c1bf0 +size 3492366880 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_M.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..c582cc8 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1880398505762a4e882817f4332c8488aba2e9c453b51140c93433a683fedec +size 4683072032 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_S.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..d55a800 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf67fee8742e8e348bed6cc0e5bf8bdf24fe8de05003dae7457d55aef26c792 +size 4457767456 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_M.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..8c5f068 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:097024c01ac8e562ea5a924005b58c08cc2fa55369191932ed3e8e274afd8a9d +size 5444829728 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_S.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..d911873 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3617c038682802785ad65f603543eebfb3d4731c31f879309b2db6788aa20dba +size 5315174944 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q6_K.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q6_K.gguf new file mode 100644 index 0000000..8ae4b59 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5a0caf2238b581ccca1b33f422f4c29bcd2afa800b5e56624e4523ad2a78e3 +size 6254197280 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.Q8_0.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.Q8_0.gguf new file mode 100644 index 0000000..d9f7371 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8c369f99f0762f0a58d7e4fcc8eb1e3d7951c45300ce2091831f5eaa5d86b4f +size 8098523680 diff --git a/Qwen2.5-7B-Open-R1-Code-GRPO.f16.gguf b/Qwen2.5-7B-Open-R1-Code-GRPO.f16.gguf new file mode 100644 index 0000000..d064cb2 --- /dev/null +++ b/Qwen2.5-7B-Open-R1-Code-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:179d5b5600bdc39c91349bb283b28cc76225b8d61a932ae876ba550739192f56 +size 15237851680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a0e2236 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-Open-R1-Code-GRPO +datasets: open-r1/verifiable-coding-problems-python +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-Open-R1-Code-GRPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-Open-R1-Code-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-Open-R1-Code-GRPO-GGUF).*** + +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/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-GRPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Open-R1-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-Open-R1-Code-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. + +