commit 2160bd72b1718816d32da916761731366e8683d2 Author: ModelHub XC Date: Wed Jul 22 04:31:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d733650 --- /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 +Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-7B-RL-GRPO-Extreme.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.IQ4_XS.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.IQ4_XS.gguf new file mode 100644 index 0000000..103af49 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7946ab69b496e4a80edd15f0fb59edba784180905a0f39d41a7c2c6151a6abe5 +size 4250298784 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q2_K.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q2_K.gguf new file mode 100644 index 0000000..596e8df --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8db4f3a6e1e8cdb4d425678c6b9b684b6d3ec8d251b15d0eb3584847aa284f2 +size 3015940512 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_L.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_L.gguf new file mode 100644 index 0000000..a43f78e --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a6774b0cb945fcc61643da1eba1dd02ed2b0730066f5d3f4707405015ab897 +size 4088459680 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_M.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_M.gguf new file mode 100644 index 0000000..c000699 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0673fa59925eb6efa6cadc2e32615231e61a0c0dfefc4ee98663b3c8acb5fc23 +size 3808391584 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_S.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_S.gguf new file mode 100644 index 0000000..eec3a71 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342c6a6f094dc40c5ebeddd5dda5de84f41800568aa3853d911b0aa1e399398b +size 3492368800 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_M.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_M.gguf new file mode 100644 index 0000000..68cda7b --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b16b8127dfe05dcaf9ccd2b9ff9f2365ac0aab3ecad2562150b1207d065dd6be +size 4683073952 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_S.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_S.gguf new file mode 100644 index 0000000..0c6af72 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb5d196b52af12ae820c2dd88179020d7fc2acce38e25fb2696ddc48179a1be +size 4457769376 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_M.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_M.gguf new file mode 100644 index 0000000..2ac4fc9 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfdff749f2546d3fdd0bdc16ffcfec1bd60979433071d919fffeed786c334c25 +size 5444831648 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_S.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_S.gguf new file mode 100644 index 0000000..4e30ffb --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b3a7d2c6e9b597121676bf0b743a77cce576f0d368c6eb35fef0284a124dcb3 +size 5315176864 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q6_K.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q6_K.gguf new file mode 100644 index 0000000..3085afc --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f72b76813b37acd30c8b9feafbce5bf6e042bec6e42b6ace20161a7c811591 +size 6254199200 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.Q8_0.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.Q8_0.gguf new file mode 100644 index 0000000..83eb46c --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7613ec641a733d84037b96d37f4fd1c1f592c41288a06a1419a4389916be1aef +size 8098525600 diff --git a/Qwen-2.5-7B-RL-GRPO-Extreme.f16.gguf b/Qwen-2.5-7B-RL-GRPO-Extreme.f16.gguf new file mode 100644 index 0000000..18609d3 --- /dev/null +++ b/Qwen-2.5-7B-RL-GRPO-Extreme.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ec38e81e17a75327ecda05b1adba694412de38f53a5d35c518eb5fb2fc7197 +size 15237853600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cb34dbb --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: luckeciano/Qwen-2.5-7B-RL-GRPO-Extreme +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: Qwen-2.5-7B-RL-GRPO-Extreme +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/luckeciano/Qwen-2.5-7B-RL-GRPO-Extreme + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-2.5-7B-RL-GRPO-Extreme-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/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-7B-RL-GRPO-Extreme-GGUF/resolve/main/Qwen-2.5-7B-RL-GRPO-Extreme.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. + +