commit 9bad9d9b13d0aeaaae21e8079f55336e672d54cc Author: ModelHub XC Date: Mon Jul 13 20:33:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Gemma-Agustus-f16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..cfa5cda --- /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-Agustus-f16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.f16.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Gemma-Agustus-f16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Gemma-Agustus-f16.IQ4_XS.gguf b/Gemma-Agustus-f16.IQ4_XS.gguf new file mode 100644 index 0000000..534d0fc --- /dev/null +++ b/Gemma-Agustus-f16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b14df059ea045f46c3e58655dd412a487dd1f97b0a43c020b0cbb9b159c1a39 +size 5223171040 diff --git a/Gemma-Agustus-f16.Q2_K.gguf b/Gemma-Agustus-f16.Q2_K.gguf new file mode 100644 index 0000000..69bef3a --- /dev/null +++ b/Gemma-Agustus-f16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a054212637ec2f830fb2716cb2977a5dd0298f2fb7ce6127521d18b4d9a929 +size 3805397984 diff --git a/Gemma-Agustus-f16.Q3_K_L.gguf b/Gemma-Agustus-f16.Q3_K_L.gguf new file mode 100644 index 0000000..f1c14d7 --- /dev/null +++ b/Gemma-Agustus-f16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7d5295449b7661278c58d954a5a46ee37298e11443fc0f3d06ddf0b1d893178 +size 5132452832 diff --git a/Gemma-Agustus-f16.Q3_K_M.gguf b/Gemma-Agustus-f16.Q3_K_M.gguf new file mode 100644 index 0000000..236526e --- /dev/null +++ b/Gemma-Agustus-f16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01fe808663712a2eb18531b02964582f3b38c22d044ac0d0dc42fc2397ec1de5 +size 4761781216 diff --git a/Gemma-Agustus-f16.Q3_K_S.gguf b/Gemma-Agustus-f16.Q3_K_S.gguf new file mode 100644 index 0000000..b8a35f0 --- /dev/null +++ b/Gemma-Agustus-f16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f081987e8568f23715416d012663ccd3c124cb3f2366c672efecdeff3ba595de +size 4337664992 diff --git a/Gemma-Agustus-f16.Q4_K_M.gguf b/Gemma-Agustus-f16.Q4_K_M.gguf new file mode 100644 index 0000000..6c0e5ec --- /dev/null +++ b/Gemma-Agustus-f16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8df3c26abbda8d37a6747d9057305769218eaf6856b89325c9facbeea4177b81 +size 5761057760 diff --git a/Gemma-Agustus-f16.Q4_K_S.gguf b/Gemma-Agustus-f16.Q4_K_S.gguf new file mode 100644 index 0000000..e5bffb3 --- /dev/null +++ b/Gemma-Agustus-f16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a5082edc86f90853cd1d0e228201d95fd805694a0e99cfaf1bb71d767de134 +size 5478925280 diff --git a/Gemma-Agustus-f16.Q5_K_M.gguf b/Gemma-Agustus-f16.Q5_K_M.gguf new file mode 100644 index 0000000..09291a5 --- /dev/null +++ b/Gemma-Agustus-f16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee179ce800d3c3020bf05bbbe6e1857cceb56e2926d10f30fc87f78ab5adc62 +size 6647366624 diff --git a/Gemma-Agustus-f16.Q5_K_S.gguf b/Gemma-Agustus-f16.Q5_K_S.gguf new file mode 100644 index 0000000..81802db --- /dev/null +++ b/Gemma-Agustus-f16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b885670f2d4cf2e0fa14376bb71a36445947ad6839184737c077c0fce66068 +size 6483592160 diff --git a/Gemma-Agustus-f16.Q6_K.gguf b/Gemma-Agustus-f16.Q6_K.gguf new file mode 100644 index 0000000..4594c9f --- /dev/null +++ b/Gemma-Agustus-f16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f2d4e59142619f139df4b79593150c93f1c2fb7969d70f2a0d30c4b83e0fb62 +size 7589069792 diff --git a/Gemma-Agustus-f16.Q8_0.gguf b/Gemma-Agustus-f16.Q8_0.gguf new file mode 100644 index 0000000..7fdb988 --- /dev/null +++ b/Gemma-Agustus-f16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804f0cfbbde96b52dad739381423442fdbeb119a2d7c29ae8213e4a18d335459 +size 9827148768 diff --git a/Gemma-Agustus-f16.f16.gguf b/Gemma-Agustus-f16.f16.gguf new file mode 100644 index 0000000..348a045 --- /dev/null +++ b/Gemma-Agustus-f16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a47e809ddcf60b317a168566c8b445c6b517e03200d5e1c62029ac72ede9bd7 +size 18490680288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b1e5dc4 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: RsGoksel/Gemma-Agustus-f16 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/RsGoksel/Gemma-Agustus-f16 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-Agustus-f16-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-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Gemma-Agustus-f16-GGUF/resolve/main/Gemma-Agustus-f16.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. + +