commit e6eb7961c8e0f724dc201aa482a3d23842a98578 Author: ModelHub XC Date: Wed Apr 22 09:40:55 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f9f070 --- /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 +Qwen2.5-1.5B-Code-GRPO-fix-reward.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-fix-reward.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.IQ4_XS.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.IQ4_XS.gguf new file mode 100644 index 0000000..aa866fd --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e440a009c91bc67724d294e9c39a78f1b711cf1a9ea099e5642485603c3bf82b +size 902183520 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q2_K.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q2_K.gguf new file mode 100644 index 0000000..f5945ea --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a08091c209cbb1a3cc1d04d1a29095460c6e3a9094f8b16105a792ba3c579779 +size 676305504 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_L.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_L.gguf new file mode 100644 index 0000000..51251ec --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3d1f80b36d7e5dea7b57a02c8ae352838e58b3db389f5abde98f54442d70fbd +size 880163424 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_M.gguf new file mode 100644 index 0000000..ee8ced9 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e561ea64bc93b38d79da5a464b65673816c20daebe38272925a0b385e575ce36 +size 824179296 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_S.gguf new file mode 100644 index 0000000..2794d02 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a022fb161b5b6bf3468a9a4d953b796ed6b44bd87e55c96d3e24907f1a64d851 +size 760945248 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_M.gguf new file mode 100644 index 0000000..a3ad0c3 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:039b7dde7eab2dd0c92875a65eacc72bb45852acc585d38e2518534d0cbb56ef +size 986049120 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_S.gguf new file mode 100644 index 0000000..c20d836 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b88143ab1a584b5fc6d3723f543a6d6a4a882fe07058aa6f459a8f735bdaae6d +size 940313184 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_M.gguf new file mode 100644 index 0000000..c187238 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9f85bdf7dc92b0e4a26600a0071b35b677f23eeaf3f1f6dca74797d0dedf983 +size 1125050976 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_S.gguf new file mode 100644 index 0000000..2adbf74 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2360c09d9803d2f300393480b5914899d99f58688d6ba0453f156005073f3e6c +size 1098730080 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q6_K.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q6_K.gguf new file mode 100644 index 0000000..10190de --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0a94f7364143689dddf54c2b5a9375663e0308199af3e9a4e45a4e7290cee6 +size 1272740448 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q8_0.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q8_0.gguf new file mode 100644 index 0000000..8dc221c --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a33442a1a80d8c106785f1669f8aa607718fbe5d4c481bf1c539780496b205b +size 1646573664 diff --git a/Qwen2.5-1.5B-Code-GRPO-fix-reward.f16.gguf b/Qwen2.5-1.5B-Code-GRPO-fix-reward.f16.gguf new file mode 100644 index 0000000..065af50 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-fix-reward.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dacd2522a3fedb844afafc9e59f399d0398a84249e869ca5d07aae122af62d9 +size 3093669984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b0f0303 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AmberYifan/Qwen2.5-1.5B-Code-GRPO-fix-reward +datasets: open-r1/verifiable-coding-problems-python +language: +- en +library_name: transformers +model_name: Qwen2.5-1.5B-Code-GRPO-fix-reward +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-1.5B-Code-GRPO-fix-reward + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-1.5B-Code-GRPO-fix-reward-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/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-fix-reward.f16.gguf) | f16 | 3.2 | 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. + +