commit 94285186910848fb0c5125ff1b0ce77b95250449 Author: ModelHub XC Date: Wed Jun 3 05:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c640a9 --- /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-SFT-Code-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-SFT-Code-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-SFT-Code-GRPO.IQ4_XS.gguf b/Qwen2.5-7B-SFT-Code-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..4d27e4d --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8d560683600d1031aa378fa5f933fb13f07324ddebb1a0757b4672842b80d4 +size 4250296192 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q2_K.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q2_K.gguf new file mode 100644 index 0000000..3cf8970 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd1f85336c9bd8208907072d32939175837885b4a3d9735ac8f128af5ca882c +size 3015937920 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_L.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..de032e3 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bad1d9ae5306aeef2dfd84904a150db2b321ed548b81e66ba6d460149c85cc +size 4088457088 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_M.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..a3f3f16 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8860abd33308ef1129395d783744cd441f24480cbcca698a0a84f25433c647f9 +size 3808388992 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_S.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..5fae500 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24ca669cad83218f2dc8eed04a0ee60dd1da7afc155cd7433813f83c8d8851f +size 3492366208 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_M.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..c89e973 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8750a7fc5b0bbf51d528f87f8933f6d5659f6ae3f3f5749b43ce09c332a0c551 +size 4683071360 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_S.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..aee289a --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ab584a989afa34802f7e4214688f9ce6011a650dce501a95500c7dfb64328ed +size 4457766784 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_M.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..849068a --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a1dbec988a78aa75a14c6b160fdd430c30f37f0e9af68d35b575b88499e149 +size 5444829056 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_S.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..900df0d --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:890da8148226eca4aaf21995f3422ad2bcbbcf185d7d1fdf2b8af7c8c51ce8e6 +size 5315174272 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q6_K.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q6_K.gguf new file mode 100644 index 0000000..01f5ab5 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f388c8f67fbc3efff5ea7e5ccf13c356f466343ec7600ecc4900cbacb25404 +size 6254196608 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.Q8_0.gguf b/Qwen2.5-7B-SFT-Code-GRPO.Q8_0.gguf new file mode 100644 index 0000000..ffa371f --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41928dfc1b4a4e0d0ff0bc80d58a6eb0325fec08eb2d8187b7495b51f9323f8 +size 8098523008 diff --git a/Qwen2.5-7B-SFT-Code-GRPO.f16.gguf b/Qwen2.5-7B-SFT-Code-GRPO.f16.gguf new file mode 100644 index 0000000..b078e75 --- /dev/null +++ b/Qwen2.5-7B-SFT-Code-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db35e4b578de3a3dbd5cbec4aea00e2c3f870bbdf2adf02c4d1d2f457d9e2c3a +size 15237851008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..871af2a --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-SFT-Code-GRPO +datasets: open-r1/verifiable-coding-problems-python +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-SFT-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-SFT-Code-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-SFT-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-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-Code-GRPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-SFT-Code-GRPO-GGUF/resolve/main/Qwen2.5-7B-SFT-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. + +