commit 37e0fd748536f9e43f2f818a5c65e7759d46dbed Author: ModelHub XC Date: Thu Jun 4 03:30:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77e8f4d --- /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-Code-GRPO-fix-reward.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Code-GRPO-fix-reward.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.IQ4_XS.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.IQ4_XS.gguf new file mode 100644 index 0000000..978c3e9 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236f8295d88cb2bf9d48031335965ead7d1bea080427804057c2dd9e4a18843f +size 4250299424 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q2_K.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q2_K.gguf new file mode 100644 index 0000000..37ef91b --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6f551523668bc24977d5fa35d4b2a9b48873b20595ed607fff13e9dd3ddffe +size 3015941152 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_L.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_L.gguf new file mode 100644 index 0000000..5219cdb --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78237af618c51a09d5c19ec9fde4b78fdfbc2dccede61cea59eb7f14296447a +size 4088460320 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_M.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_M.gguf new file mode 100644 index 0000000..3fe1d62 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b99587c027639c8a81f5e8eb1f306ecba1221ba1bfea58c005fa90d1ae902b +size 3808392224 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_S.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_S.gguf new file mode 100644 index 0000000..39fa3ac --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3d568d5615019d9dad249d2fd08f7ebf48386009466d6bc012248f1d347045 +size 3492369440 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_M.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_M.gguf new file mode 100644 index 0000000..b49eaf4 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d44d7330f6cee38e72181cd9c91b26b8cf55d03bbf98b712e7d7282060c7e0f9 +size 4683074592 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_S.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_S.gguf new file mode 100644 index 0000000..afd856a --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a7a192fdc5460c9c82bd31ca36edd8f4ed77e5f1e58d21ad25fe59d28ee848 +size 4457770016 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_M.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_M.gguf new file mode 100644 index 0000000..f56dbf5 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b587908eac50ab8d44f756a4cc1d91237df7a54e95bfe6beca08ed8f2aa1b15 +size 5444832288 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_S.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_S.gguf new file mode 100644 index 0000000..aa74937 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ab3887870772fe6f3a73548529aff77fbbf3f6965dc4a4d5841c1f594e28809 +size 5315177504 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q6_K.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q6_K.gguf new file mode 100644 index 0000000..4b339b0 --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ea1da9677d806527800722609ce19c03199a5eef62c8bbf1a58a07010437f9 +size 6254199840 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.Q8_0.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.Q8_0.gguf new file mode 100644 index 0000000..32afbdb --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a622607d8ab04288b518e57ce1bb7529655251d3cd61c49521bc96a8e41d158b +size 8098526240 diff --git a/Qwen2.5-7B-Code-GRPO-fix-reward.f16.gguf b/Qwen2.5-7B-Code-GRPO-fix-reward.f16.gguf new file mode 100644 index 0000000..72cd3cc --- /dev/null +++ b/Qwen2.5-7B-Code-GRPO-fix-reward.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80e73b20a0388e0be6ed02b1df7ea2bf57be666db43238d8ffea4179bba66480 +size 15237854240 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1d38772 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-Code-GRPO-fix-reward +datasets: open-r1/verifiable-coding-problems-python +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-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/Qwen2.5-7B-Code-GRPO-fix-reward + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-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/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Code-GRPO-fix-reward-GGUF/resolve/main/Qwen2.5-7B-Code-GRPO-fix-reward.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. + +