commit e00c504e551630277474aa90c4cce96190c7ab14 Author: ModelHub XC Date: Thu Jun 4 17:31:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-1b-reasoning-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..745c32b --- /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 +gemma-3-1b-reasoning-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-reasoning-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3e6e3c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: ertghiu256/gemma-3-1b-reasoning-GRPO +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma3_text +--- +## About + + + + + + +static quants of https://huggingface.co/ertghiu256/gemma-3-1b-reasoning-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-1b-reasoning-GRPO-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/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-reasoning-GRPO-GGUF/resolve/main/gemma-3-1b-reasoning-GRPO.f16.gguf) | f16 | 2.1 | 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. + + diff --git a/gemma-3-1b-reasoning-GRPO.IQ4_XS.gguf b/gemma-3-1b-reasoning-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..bb3090f --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df955b55fd1ba95ad5760d7c63c342c129efa3f91785fdb3a3a822498d195713 +size 718168192 diff --git a/gemma-3-1b-reasoning-GRPO.Q2_K.gguf b/gemma-3-1b-reasoning-GRPO.Q2_K.gguf new file mode 100644 index 0000000..3a0c65b --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befa2721f88134253580f2fe938f122d266eec27211c641470bfd64f7df3df13 +size 689815168 diff --git a/gemma-3-1b-reasoning-GRPO.Q3_K_L.gguf b/gemma-3-1b-reasoning-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..f110a06 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8879eab65660d8aa3e7d3e6e89398c99cb14e68d2d6fd8f9f556a7904787cec9 +size 751576192 diff --git a/gemma-3-1b-reasoning-GRPO.Q3_K_M.gguf b/gemma-3-1b-reasoning-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..057e740 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b47ceefd85aed7596af9691c91b8e833c66d75c7d700b8db520b185c5cdcec +size 722416768 diff --git a/gemma-3-1b-reasoning-GRPO.Q3_K_S.gguf b/gemma-3-1b-reasoning-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..591c9a2 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb46e1550b0d288ef43dc5b70d09c8f2300d5463bcb1a4700082a6e5b0fa67d +size 688856704 diff --git a/gemma-3-1b-reasoning-GRPO.Q4_K_M.gguf b/gemma-3-1b-reasoning-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..72295ec --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b82d50a49ebe8809aada51f9cb8197f85003538ba2573a8feb70a0fbdedd1963 +size 806058880 diff --git a/gemma-3-1b-reasoning-GRPO.Q4_K_S.gguf b/gemma-3-1b-reasoning-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..d911b83 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8639585f8034493c87a944bed45b03c987c0f9b9137f742e54bb12c1449dbe64 +size 780993664 diff --git a/gemma-3-1b-reasoning-GRPO.Q5_K_M.gguf b/gemma-3-1b-reasoning-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..3ae771c --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b128b5152ab30c0eba68a87876b1b6ab6e64a41a9a6370bc7117a0ff6a2b14d +size 851346304 diff --git a/gemma-3-1b-reasoning-GRPO.Q5_K_S.gguf b/gemma-3-1b-reasoning-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..4d536e4 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a4512f9cd63ac3c92c472850d4644b197fe44913230da5d201783932dd30b8 +size 836400256 diff --git a/gemma-3-1b-reasoning-GRPO.Q6_K.gguf b/gemma-3-1b-reasoning-GRPO.Q6_K.gguf new file mode 100644 index 0000000..92114e6 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2021414d5c9a1d2d063e979923baec3cdc0d6eed595a3d64c878bf5d2ae0e7c0 +size 1011739264 diff --git a/gemma-3-1b-reasoning-GRPO.Q8_0.gguf b/gemma-3-1b-reasoning-GRPO.Q8_0.gguf new file mode 100644 index 0000000..95652ac --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:624ede275646295ba0591840a6ac658b456c5ef4380838d74fd458bce6753d2a +size 1069307008 diff --git a/gemma-3-1b-reasoning-GRPO.f16.gguf b/gemma-3-1b-reasoning-GRPO.f16.gguf new file mode 100644 index 0000000..f2da736 --- /dev/null +++ b/gemma-3-1b-reasoning-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27a127dd99e05cb07abbc29449bdd0bf1e05c4412c3c335291656d16587f6ae9 +size 2006574208