commit 3050262302a2d361ab42f32e78adaf96770430c7 Author: ModelHub XC Date: Thu Jun 25 18:43:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ce0f725 --- /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 +LiA-Reasoning-Qwen-2.5-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LiA-Reasoning-Qwen-2.5-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.IQ4_XS.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..321b5e4 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f1b1317cb2f5302f97924f33a53208cd57d621bfe619097bf5e8bbad62cd5c8 +size 1753185664 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q2_K.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q2_K.gguf new file mode 100644 index 0000000..853a66a --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825d501e9483cac3e762f6ebf27536d24adcdbf7ea1c12820da90174228a63c7 +size 1274756480 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_L.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..8e5e268 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47bb2d0e11e79d83cbc3c7a1484f17af0e7ff65d0323698b0188a88cceb1fa82 +size 1707392384 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_M.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..fe93b55 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a5730e7da945e47ab7bd9c50cf41d6e69049278ca95a80856549a99a57d0d1 +size 1590476160 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_S.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..5608ca0 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d7ae350b7112cd0829054db73be52de3c77b8ffd61a080dbac1bf286f40938 +size 1454357888 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_M.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..acd7caf --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f253d1feb6f17cb38b39d07cba7a153fdf1703d9e499ecd9b692959017ece9fd +size 1929903488 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_S.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..570472b --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f72a938e450669bb4daad380ed7fb4f46ce964b752a19cf69900db5784373b +size 1834384768 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_M.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..3c8a3ce --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46c40c7db26f9297f027e6f41e25ea06a8f5a0c439d515e62d84b34abcf17e11 +size 2224815488 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_S.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..8b08813 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f403c6eaad0b90816ee398093ac4eee75c0f0f8e709308fae635b63846265ecc +size 2169666944 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q6_K.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q6_K.gguf new file mode 100644 index 0000000..598b616 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b645b68815e328e8226a09f8c3e366512404f501060d0d290a455dd6ff93837 +size 2538159488 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.Q8_0.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.Q8_0.gguf new file mode 100644 index 0000000..efebd1d --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd76b10c56ba547846578cedb01749f39983c9e6a3071f59227293b52ad2ac2d +size 3285476736 diff --git a/LiA-Reasoning-Qwen-2.5-GRPO.f16.gguf b/LiA-Reasoning-Qwen-2.5-GRPO.f16.gguf new file mode 100644 index 0000000..94d5e57 --- /dev/null +++ b/LiA-Reasoning-Qwen-2.5-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c082e4b6866eed5558710a4fdb73ff914e684a477a1af64a3ef854d317740bde +size 6178317696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79852ba --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: Creekside/LiA-Reasoning-Qwen-2.5-GRPO +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- gguf +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/Creekside/LiA-Reasoning-Qwen-2.5-GRPO + + +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/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LiA-Reasoning-Qwen-2.5-GRPO-GGUF/resolve/main/LiA-Reasoning-Qwen-2.5-GRPO.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. + +