commit 79fe9875d8691f328967b18a79d2d4f641a1c6cd Author: ModelHub XC Date: Thu Jun 4 02:43:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Proto_RP-Gemma2-2B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5783fbf --- /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 +Proto_RP-Gemma2-2B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Proto_RP-Gemma2-2B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Proto_RP-Gemma2-2B.IQ4_XS.gguf b/Proto_RP-Gemma2-2B.IQ4_XS.gguf new file mode 100644 index 0000000..6084876 --- /dev/null +++ b/Proto_RP-Gemma2-2B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f9a0e8bd11459f5f5eda8418c3bdff2f4665677c94467a3a4f25960c41aff8 +size 1576205472 diff --git a/Proto_RP-Gemma2-2B.Q2_K.gguf b/Proto_RP-Gemma2-2B.Q2_K.gguf new file mode 100644 index 0000000..288b9cd --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f9a6a68f6304e2d917f162db9545c7da53d6d92b61238bfd8f1168bdeb3fd7 +size 1229831328 diff --git a/Proto_RP-Gemma2-2B.Q3_K_L.gguf b/Proto_RP-Gemma2-2B.Q3_K_L.gguf new file mode 100644 index 0000000..1dd47c2 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e8e36ef8ac5b198d729ad91645b34af8fe62408b8c141c467c6e8f0c62d34f +size 1550437536 diff --git a/Proto_RP-Gemma2-2B.Q3_K_M.gguf b/Proto_RP-Gemma2-2B.Q3_K_M.gguf new file mode 100644 index 0000000..9c7713b --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77885e79fcdc86ff81e032ca0ea6b6fc834562580e523516022b4e9aee2e00c2 +size 1461669024 diff --git a/Proto_RP-Gemma2-2B.Q3_K_S.gguf b/Proto_RP-Gemma2-2B.Q3_K_S.gguf new file mode 100644 index 0000000..1c4a606 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f19c719c951c98b63b678d6ee49869eed80ca5c978d47081edd5e28683fbdcca +size 1360661664 diff --git a/Proto_RP-Gemma2-2B.Q4_K_M.gguf b/Proto_RP-Gemma2-2B.Q4_K_M.gguf new file mode 100644 index 0000000..b84e8f8 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c229ffe0e8a920e0f239ff300ace9fc32986c0f1b2884a42e00ddfa7f1d68010 +size 1708584096 diff --git a/Proto_RP-Gemma2-2B.Q4_K_S.gguf b/Proto_RP-Gemma2-2B.Q4_K_S.gguf new file mode 100644 index 0000000..fc1ddbf --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d76f939f21cdc45719ccb9c80832741fea96517d9a7f490d4e1e9aa777d0644 +size 1638653088 diff --git a/Proto_RP-Gemma2-2B.Q5_K_M.gguf b/Proto_RP-Gemma2-2B.Q5_K_M.gguf new file mode 100644 index 0000000..d25c2f2 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db729e414a488fb7ace4e33c8520a4704528b81508e66d96af8c4c90970bad9c +size 1923280032 diff --git a/Proto_RP-Gemma2-2B.Q5_K_S.gguf b/Proto_RP-Gemma2-2B.Q5_K_S.gguf new file mode 100644 index 0000000..a432a88 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250739d90d4820d3474c701be484c815b42c75cb1c3a49e4ac75198fc51cfbca +size 1882545312 diff --git a/Proto_RP-Gemma2-2B.Q6_K.gguf b/Proto_RP-Gemma2-2B.Q6_K.gguf new file mode 100644 index 0000000..b687600 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593f574b3466cf1ad114b31b6bc9d7cda98e8aa4be76df597333859568ed82c8 +size 2151394464 diff --git a/Proto_RP-Gemma2-2B.Q8_0.gguf b/Proto_RP-Gemma2-2B.Q8_0.gguf new file mode 100644 index 0000000..6a285a0 --- /dev/null +++ b/Proto_RP-Gemma2-2B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9696db46957e7c59e81904c468b7b84e02affec1bb4174e4d1b6c04eb7882c9 +size 2784496800 diff --git a/Proto_RP-Gemma2-2B.f16.gguf b/Proto_RP-Gemma2-2B.f16.gguf new file mode 100644 index 0000000..05fb67d --- /dev/null +++ b/Proto_RP-Gemma2-2B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d269692e25db751ee853bf0c4c467455ad0a007ba1a33ffdd677020c1de6c580 +size 5235215520 diff --git a/README.md b/README.md new file mode 100644 index 0000000..eda0715 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: Novaciano/Proto_RP-Gemma2-2B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Novaciano/Proto_RP-Gemma2-2B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Proto_RP-Gemma2-2B-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/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q3_K_S.gguf) | Q3_K_S | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q3_K_M.gguf) | Q3_K_M | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.IQ4_XS.gguf) | IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q5_K_M.gguf) | Q5_K_M | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Proto_RP-Gemma2-2B-GGUF/resolve/main/Proto_RP-Gemma2-2B.f16.gguf) | f16 | 5.3 | 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. + +