commit ef399ced3d081eaf41aec9a095e229a5c5de44aa Author: ModelHub XC Date: Mon May 25 12:25:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-1b-it-grpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..50d5d02 --- /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-it-grpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-1b-it-grpo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..134be88 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: tatsuyaaaaaaa/gemma-3-1b-it-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/tatsuyaaaaaaa/gemma-3-1b-it-grpo + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-3-1b-it-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-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-grpo.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-1b-it-grpo-GGUF/resolve/main/gemma-3-1b-it-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-it-grpo.IQ4_XS.gguf b/gemma-3-1b-it-grpo.IQ4_XS.gguf new file mode 100644 index 0000000..6cfbe74 --- /dev/null +++ b/gemma-3-1b-it-grpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb2a3024e9ed618b3b1583161682ee4d7453cda221eb7ae4efb3a06352779aed +size 718168128 diff --git a/gemma-3-1b-it-grpo.Q2_K.gguf b/gemma-3-1b-it-grpo.Q2_K.gguf new file mode 100644 index 0000000..64cacd2 --- /dev/null +++ b/gemma-3-1b-it-grpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4973f2b5ed9d52dd02627b09406690de8839739fe4fa2849f2c1a32da43e1867 +size 689815104 diff --git a/gemma-3-1b-it-grpo.Q3_K_L.gguf b/gemma-3-1b-it-grpo.Q3_K_L.gguf new file mode 100644 index 0000000..7d129aa --- /dev/null +++ b/gemma-3-1b-it-grpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74e81991f6bbd9b675290092384698404c2d557dffadb677921ce4bc39fbd78b +size 751576128 diff --git a/gemma-3-1b-it-grpo.Q3_K_M.gguf b/gemma-3-1b-it-grpo.Q3_K_M.gguf new file mode 100644 index 0000000..2b5d85a --- /dev/null +++ b/gemma-3-1b-it-grpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8665bf6724530a0451fabe60cefe651f8c3297d9b45bd7533000278b9f5188 +size 722416704 diff --git a/gemma-3-1b-it-grpo.Q3_K_S.gguf b/gemma-3-1b-it-grpo.Q3_K_S.gguf new file mode 100644 index 0000000..37a6f1e --- /dev/null +++ b/gemma-3-1b-it-grpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872860d58a25b0aa14fc6fc3aa53ccc2a79d694213e1dc52c7fdc427e505b95c +size 688856640 diff --git a/gemma-3-1b-it-grpo.Q4_K_M.gguf b/gemma-3-1b-it-grpo.Q4_K_M.gguf new file mode 100644 index 0000000..a565f93 --- /dev/null +++ b/gemma-3-1b-it-grpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cba923d1c87d0707542feb1f50c732084244429cd2b4ed3d2c12e4b307d348c4 +size 806058816 diff --git a/gemma-3-1b-it-grpo.Q4_K_S.gguf b/gemma-3-1b-it-grpo.Q4_K_S.gguf new file mode 100644 index 0000000..c86840e --- /dev/null +++ b/gemma-3-1b-it-grpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7594bf839e5671b5ff781ab1c8d6a4c9edf555104400d46d0420f9b98ab410df +size 780993600 diff --git a/gemma-3-1b-it-grpo.Q5_K_M.gguf b/gemma-3-1b-it-grpo.Q5_K_M.gguf new file mode 100644 index 0000000..ecea926 --- /dev/null +++ b/gemma-3-1b-it-grpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610d08782950f8eaf63711a3a1d8d882ca8392389c710ad31c80f29700e2074f +size 851346240 diff --git a/gemma-3-1b-it-grpo.Q5_K_S.gguf b/gemma-3-1b-it-grpo.Q5_K_S.gguf new file mode 100644 index 0000000..0d516aa --- /dev/null +++ b/gemma-3-1b-it-grpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d944890f86d41cc8730154c0e9e13a9a8e7acf9cee739fe58adceac907a3404d +size 836400192 diff --git a/gemma-3-1b-it-grpo.Q6_K.gguf b/gemma-3-1b-it-grpo.Q6_K.gguf new file mode 100644 index 0000000..0c14842 --- /dev/null +++ b/gemma-3-1b-it-grpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d6a9922413b5795bbc7df86613ce62bb9b99f7f455e5d0a248a4918a71e387c +size 1011739200 diff --git a/gemma-3-1b-it-grpo.Q8_0.gguf b/gemma-3-1b-it-grpo.Q8_0.gguf new file mode 100644 index 0000000..ba8ffe3 --- /dev/null +++ b/gemma-3-1b-it-grpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58926f691112cfb3c17da3ba0d4deb827ef844cfe300dd5e1c4578103772ba23 +size 1069306944 diff --git a/gemma-3-1b-it-grpo.f16.gguf b/gemma-3-1b-it-grpo.f16.gguf new file mode 100644 index 0000000..4e62ec1 --- /dev/null +++ b/gemma-3-1b-it-grpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5725382473f81069c29daf5e20bc5d8a4e251d40500b25d2307bce3e8b5280a0 +size 2006574144