commit 6d03aedd58766d9e10be577c7ee7dd4342b7d6f6 Author: ModelHub XC Date: Mon Jun 15 07:50:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-4b-it-rude-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8116476 --- /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-4b-it-rude.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-4b-it-rude.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1313a0d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Eric111/gemma-3-4b-it-rude +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Eric111/gemma-3-4b-it-rude + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4b-it-rude-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-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-4b-it-rude-GGUF/resolve/main/gemma-4b-it-rude.f16.gguf) | f16 | 7.9 | 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-4b-it-rude.IQ4_XS.gguf b/gemma-4b-it-rude.IQ4_XS.gguf new file mode 100644 index 0000000..70cb313 --- /dev/null +++ b/gemma-4b-it-rude.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e02ef03fa86370400c974f7f8a535771a1e3829d17ae5b0133a41434c2c38c6 +size 2279624736 diff --git a/gemma-4b-it-rude.Q2_K.gguf b/gemma-4b-it-rude.Q2_K.gguf new file mode 100644 index 0000000..a26ac2d --- /dev/null +++ b/gemma-4b-it-rude.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5133ed4d10e0d2811f585cba2b9f212a2467969835a80ac99fb3a6832f1110e4 +size 1729163296 diff --git a/gemma-4b-it-rude.Q3_K_L.gguf b/gemma-4b-it-rude.Q3_K_L.gguf new file mode 100644 index 0000000..37bb9ba --- /dev/null +++ b/gemma-4b-it-rude.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b540302cd7ebbca829f82ce90463a593911f471c3e64567c8e275210d85b78fc +size 2236084256 diff --git a/gemma-4b-it-rude.Q3_K_M.gguf b/gemma-4b-it-rude.Q3_K_M.gguf new file mode 100644 index 0000000..36e99fa --- /dev/null +++ b/gemma-4b-it-rude.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcd0a5d77b643e868af5cd073a5fda066da4b55f4cc0d523d5b96f8ffd8e2da +size 2098458656 diff --git a/gemma-4b-it-rude.Q3_K_S.gguf b/gemma-4b-it-rude.Q3_K_S.gguf new file mode 100644 index 0000000..37bf87e --- /dev/null +++ b/gemma-4b-it-rude.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86fd916f0d2c9cdc8babbe4772572b841d733f258d1f4f92546fd0f3674ef5ca +size 1937362976 diff --git a/gemma-4b-it-rude.Q4_K_M.gguf b/gemma-4b-it-rude.Q4_K_M.gguf new file mode 100644 index 0000000..33a48a0 --- /dev/null +++ b/gemma-4b-it-rude.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a268a3786e0a9b96b47d33a9c11ad26883a43517ddc34883431ec0fc08ad4d2 +size 2489892896 diff --git a/gemma-4b-it-rude.Q4_K_S.gguf b/gemma-4b-it-rude.Q4_K_S.gguf new file mode 100644 index 0000000..6b77fcd --- /dev/null +++ b/gemma-4b-it-rude.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50c57b15535f60298ef64d093dc5201ca485e285d462733e5a498aa8f792946 +size 2377928736 diff --git a/gemma-4b-it-rude.Q5_K_M.gguf b/gemma-4b-it-rude.Q5_K_M.gguf new file mode 100644 index 0000000..16afecc --- /dev/null +++ b/gemma-4b-it-rude.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1298abbf25b775ed87f407d12e036bd246144f303199a27f00aefb93c4bf72 +size 2829697056 diff --git a/gemma-4b-it-rude.Q5_K_S.gguf b/gemma-4b-it-rude.Q5_K_S.gguf new file mode 100644 index 0000000..0efce01 --- /dev/null +++ b/gemma-4b-it-rude.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e45b3fd3d4931b61a9207629e91551665e7f443458a8d3737dc346eb941323 +size 2764591136 diff --git a/gemma-4b-it-rude.Q6_K.gguf b/gemma-4b-it-rude.Q6_K.gguf new file mode 100644 index 0000000..ad34151 --- /dev/null +++ b/gemma-4b-it-rude.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945f16c74a4931ca0938b6b6f8212cfac1ac8fe533fb3cc2b8b59959092f13d9 +size 3190738976 diff --git a/gemma-4b-it-rude.Q8_0.gguf b/gemma-4b-it-rude.Q8_0.gguf new file mode 100644 index 0000000..b335bb0 --- /dev/null +++ b/gemma-4b-it-rude.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c909e382f99c7cf256b9bf394eb7513b3c016df9f1eec910fd5442be1691234 +size 4130401056 diff --git a/gemma-4b-it-rude.f16.gguf b/gemma-4b-it-rude.f16.gguf new file mode 100644 index 0000000..41ab557 --- /dev/null +++ b/gemma-4b-it-rude.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27c7cef10e0fac9559a2498b6671f56045cc1d8f66605061fa034b425c9acbc4 +size 7767802656