commit c17acc3fd640b6b3e9f9264357326ffdd1f5112c Author: ModelHub XC Date: Mon Oct 5 05:05:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AetherGemma-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75ba0c9 --- /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 +AetherGemma.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.f16.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AetherGemma.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AetherGemma.IQ4_XS.gguf b/AetherGemma.IQ4_XS.gguf new file mode 100644 index 0000000..07a0841 --- /dev/null +++ b/AetherGemma.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c7019a247b26af1eb23e0567661974c399ad37fa1ce800b9f32a01f7acaa57d +size 5223171872 diff --git a/AetherGemma.Q2_K.gguf b/AetherGemma.Q2_K.gguf new file mode 100644 index 0000000..2469f1a --- /dev/null +++ b/AetherGemma.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3608703bfdb1c727c737df90b410e9a0066e3e8f98d3ddb92a83eeaa986316c +size 3805398816 diff --git a/AetherGemma.Q3_K_L.gguf b/AetherGemma.Q3_K_L.gguf new file mode 100644 index 0000000..767e877 --- /dev/null +++ b/AetherGemma.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454545623104213757067d713aa59e671eeb4b1f2118cad551d402abe78dd94c +size 5132453664 diff --git a/AetherGemma.Q3_K_M.gguf b/AetherGemma.Q3_K_M.gguf new file mode 100644 index 0000000..279cbe7 --- /dev/null +++ b/AetherGemma.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b9efb3077b629dd6d7a82473d6416619b9fd9fb9d893d5aae40f7a34d118146 +size 4761782048 diff --git a/AetherGemma.Q3_K_S.gguf b/AetherGemma.Q3_K_S.gguf new file mode 100644 index 0000000..abc15d0 --- /dev/null +++ b/AetherGemma.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d15132719b3222025848d4e3b751ec50578af64a5b1399a5e76fecab7eecc7d +size 4337665824 diff --git a/AetherGemma.Q4_K_M.gguf b/AetherGemma.Q4_K_M.gguf new file mode 100644 index 0000000..c59cc4e --- /dev/null +++ b/AetherGemma.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:747cceaac255dc156875c51aef206c0607a89f1c893b02de93347f8dcb8e16d3 +size 5761058592 diff --git a/AetherGemma.Q4_K_S.gguf b/AetherGemma.Q4_K_S.gguf new file mode 100644 index 0000000..0573a57 --- /dev/null +++ b/AetherGemma.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ac546b9c3e9dabea5034367dceb66366f547146a843f6993b1801b299b15c83 +size 5478926112 diff --git a/AetherGemma.Q5_K_M.gguf b/AetherGemma.Q5_K_M.gguf new file mode 100644 index 0000000..6b5719a --- /dev/null +++ b/AetherGemma.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3cb68c90c1351bc1ccdbe8783ca9b41e213150dde1643bf573d60d77cd6fdd9 +size 6647367456 diff --git a/AetherGemma.Q5_K_S.gguf b/AetherGemma.Q5_K_S.gguf new file mode 100644 index 0000000..25f57ba --- /dev/null +++ b/AetherGemma.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f3a90bc38473c3f574e9dffb7bbd5fd84cb14eb74a89795b693e022efbd2e9 +size 6483592992 diff --git a/AetherGemma.Q6_K.gguf b/AetherGemma.Q6_K.gguf new file mode 100644 index 0000000..210e594 --- /dev/null +++ b/AetherGemma.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f17ec6f92f54f06d02ccc40fe7501f1cb31165850bf762c0c5652b1563d0db9 +size 7589070624 diff --git a/AetherGemma.Q8_0.gguf b/AetherGemma.Q8_0.gguf new file mode 100644 index 0000000..44f50cb --- /dev/null +++ b/AetherGemma.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f054c1769be3e29d3acbbb72f51aecba6924441eadc13c20ffc5262063c373d +size 9827149600 diff --git a/AetherGemma.f16.gguf b/AetherGemma.f16.gguf new file mode 100644 index 0000000..76ca1d2 --- /dev/null +++ b/AetherGemma.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c2e744b8ff7dd779520a717b0641b3f10f71560d3014d1861048c08efbbdf4d +size 18490681120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..43cf6f9 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Daemontatox/AetherGemma +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gemma2 +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/Daemontatox/AetherGemma + + +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/AetherGemma-GGUF/resolve/main/AetherGemma.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AetherGemma-GGUF/resolve/main/AetherGemma.f16.gguf) | f16 | 18.6 | 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. + +