commit 8b44b47df260e62f2dc5f00521b5d7fe662d4cab Author: ModelHub XC Date: Fri May 22 10:04:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-3-4b-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2cf8aac --- /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-3-4b-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-3-4b-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..55281f5 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: lunahr/gemma-3-4b-abliterated +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/lunahr/gemma-3-4b-abliterated + + +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-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-3-4b-abliterated-GGUF/resolve/main/gemma-3-4b-abliterated.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-3-4b-abliterated.IQ4_XS.gguf b/gemma-3-4b-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..95b0fc0 --- /dev/null +++ b/gemma-3-4b-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9218035b2035ccbced9abf6b6b5207cfd4fcd4803e12677327dc9dfb5d8d3aa0 +size 2279626304 diff --git a/gemma-3-4b-abliterated.Q2_K.gguf b/gemma-3-4b-abliterated.Q2_K.gguf new file mode 100644 index 0000000..f6716c6 --- /dev/null +++ b/gemma-3-4b-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75e5f0748af40f2a367f084fa838e33e367f44e1c781f2853ee9b5c5e5022606 +size 1729164864 diff --git a/gemma-3-4b-abliterated.Q3_K_L.gguf b/gemma-3-4b-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..60c0054 --- /dev/null +++ b/gemma-3-4b-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70e138544061d0edb32a734abde64ba999ecc485dc264dbb9963bd5dfd39f2f0 +size 2236085824 diff --git a/gemma-3-4b-abliterated.Q3_K_M.gguf b/gemma-3-4b-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..5fd555c --- /dev/null +++ b/gemma-3-4b-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a71d062ecd6a556b00263e092d5189c3566aab3c11703fe755e6356f40664d87 +size 2098460224 diff --git a/gemma-3-4b-abliterated.Q3_K_S.gguf b/gemma-3-4b-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..70a7bff --- /dev/null +++ b/gemma-3-4b-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eae6ec478c04f22a77a0595c6cdde78549fbec84ba4d0a4c36acb933a3c6d66 +size 1937364544 diff --git a/gemma-3-4b-abliterated.Q4_K_M.gguf b/gemma-3-4b-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..557eb27 --- /dev/null +++ b/gemma-3-4b-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ef222a343bbf23972dff55dc818d8b77f202a724aa2f1765ac60d0918aee55b +size 2489894464 diff --git a/gemma-3-4b-abliterated.Q4_K_S.gguf b/gemma-3-4b-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..561b468 --- /dev/null +++ b/gemma-3-4b-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13b4b982dfa38686aa1fbdd77e4c1a02fd6d066a15739b1b485783f323d1205f +size 2377930304 diff --git a/gemma-3-4b-abliterated.Q5_K_M.gguf b/gemma-3-4b-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..eeedaa0 --- /dev/null +++ b/gemma-3-4b-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe5daa4abefb9091d4f68caaaeae3b21139615c388bb261beece36a50590955 +size 2829698624 diff --git a/gemma-3-4b-abliterated.Q5_K_S.gguf b/gemma-3-4b-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..741aaea --- /dev/null +++ b/gemma-3-4b-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:702bfeac086d3e9dfa0d1f91ac309442dc99fb4f99c9a93a5256b0e935259abd +size 2764592704 diff --git a/gemma-3-4b-abliterated.Q6_K.gguf b/gemma-3-4b-abliterated.Q6_K.gguf new file mode 100644 index 0000000..2db3c21 --- /dev/null +++ b/gemma-3-4b-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4323e7316c7c4bca2a650bb51f5ff3da13d760d09454006dee156d6474437bb9 +size 3190740544 diff --git a/gemma-3-4b-abliterated.Q8_0.gguf b/gemma-3-4b-abliterated.Q8_0.gguf new file mode 100644 index 0000000..ee920cc --- /dev/null +++ b/gemma-3-4b-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f90e7921e465b3c6e0b1f9cdde2228ab2c841968edf2a22904976e492b8cd096 +size 4130402624 diff --git a/gemma-3-4b-abliterated.f16.gguf b/gemma-3-4b-abliterated.f16.gguf new file mode 100644 index 0000000..bdddf4e --- /dev/null +++ b/gemma-3-4b-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ef1a9562d0a748799142e3d1d01301263e544979746f69f47fcfbcfc81d988 +size 7767804224