commit a6a47acecd7ac812902f420774419e606e47106a Author: ModelHub XC Date: Tue Sep 22 13:12:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74beddb --- /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 +Cedar-GRPO-Qwen2.5-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Cedar-GRPO-Qwen2.5-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Cedar-GRPO-Qwen2.5-3B.IQ4_XS.gguf b/Cedar-GRPO-Qwen2.5-3B.IQ4_XS.gguf new file mode 100644 index 0000000..9321fef --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de89dbf63b90cfe9f317b1205882e996fecc5e13f13ccc2c488a03ec0cab0d1c +size 1753185856 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q2_K.gguf b/Cedar-GRPO-Qwen2.5-3B.Q2_K.gguf new file mode 100644 index 0000000..c3ca378 --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e31f4a4ba89c16c559b85b3855d1d43787a6785a487bf5d2e763d8f9b14f3b3b +size 1274756672 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q3_K_L.gguf b/Cedar-GRPO-Qwen2.5-3B.Q3_K_L.gguf new file mode 100644 index 0000000..4db7b7f --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8400619f7f181048edbaed0480b66cf8b6786080059c4ac2876fce016fa2468c +size 1707392576 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q3_K_M.gguf b/Cedar-GRPO-Qwen2.5-3B.Q3_K_M.gguf new file mode 100644 index 0000000..9e8f4a3 --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32c3e3188714b5a7c899b19d0617f2b772fbded163f314344a9049c944ee9eb2 +size 1590476352 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q3_K_S.gguf b/Cedar-GRPO-Qwen2.5-3B.Q3_K_S.gguf new file mode 100644 index 0000000..cd010cc --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde397dad79d723525d23c59cfda4b15fe1cb4129a1d14425c9d5bc677552fa3 +size 1454358080 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q4_K_M.gguf b/Cedar-GRPO-Qwen2.5-3B.Q4_K_M.gguf new file mode 100644 index 0000000..3106e55 --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4f584cc4e781df51851688fb1cab5a85858a08cf532e8c98c6caa0f1abb73d +size 1929903680 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q4_K_S.gguf b/Cedar-GRPO-Qwen2.5-3B.Q4_K_S.gguf new file mode 100644 index 0000000..5a485ef --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4f151cc4174c5ab5e46a5ca5bcd029aa7604699d39dcc7c6e68f5f8f84b812 +size 1834384960 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q5_K_M.gguf b/Cedar-GRPO-Qwen2.5-3B.Q5_K_M.gguf new file mode 100644 index 0000000..2a6dcfd --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64dfa7e40d2286da085666a19a109b3994826c0d03180c4a0e78a6c69250ae5d +size 2224815680 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q5_K_S.gguf b/Cedar-GRPO-Qwen2.5-3B.Q5_K_S.gguf new file mode 100644 index 0000000..d016fd9 --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adc6f4cb9c0b1f53308c8b2f69bc1358ccaebd09eb3a1b17635ede0b11f89d9f +size 2169667136 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q6_K.gguf b/Cedar-GRPO-Qwen2.5-3B.Q6_K.gguf new file mode 100644 index 0000000..8e3c23a --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f401c193b462f3b8e0bd55a683f1feb8d4593f5db9e8cd00ab4245281db3320 +size 2538159680 diff --git a/Cedar-GRPO-Qwen2.5-3B.Q8_0.gguf b/Cedar-GRPO-Qwen2.5-3B.Q8_0.gguf new file mode 100644 index 0000000..0c71fd2 --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c08da9a1ef4975d5ec9eedef82a0d6f9d3fd2182a4f8dd3030b6eb9ed45deb4a +size 3285476928 diff --git a/Cedar-GRPO-Qwen2.5-3B.f16.gguf b/Cedar-GRPO-Qwen2.5-3B.f16.gguf new file mode 100644 index 0000000..de8d21d --- /dev/null +++ b/Cedar-GRPO-Qwen2.5-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0def04b537b423caecc22134a056d7d08b80582bcde2e98b28c36f9eef85a1bd +size 6178317888 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5b791e6 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: zbeeb/Qwen2.5-3B-GRPO-Staleness-2 +datasets: +- zbeeb/Staleness-GRPO-DAPO-Math-17k +language: +- en +- zh +library_name: transformers +license: other +license_link: LICENSE +license_name: qwen-research +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- grpo +- math +- reinforcement-learning +- qwen2 +- staleness-grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zbeeb/Qwen2.5-3B-GRPO-Staleness-2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Cedar-GRPO-Qwen2.5-3B-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/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Cedar-GRPO-Qwen2.5-3B-GGUF/resolve/main/Cedar-GRPO-Qwen2.5-3B.f16.gguf) | f16 | 6.3 | 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. + +