commit 2a695f0d2beb441de9adfd60908925703712eefc Author: ModelHub XC Date: Mon Jun 15 09:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma2-gutenberg-9B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2353500 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma2-gutenberg-9B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fd30291 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: nbeerbower/gemma2-gutenberg-9B +datasets: +- jondurbin/gutenberg-dpo-v0.1 +language: +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/gemma2-gutenberg-9B + + +static quants are available at https://huggingface.co/mradermacher/gemma2-gutenberg-9B-GGUF +## 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/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma2-gutenberg-9B-i1-GGUF/resolve/main/gemma2-gutenberg-9B.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/gemma2-gutenberg-9B.i1-IQ1_M.gguf b/gemma2-gutenberg-9B.i1-IQ1_M.gguf new file mode 100644 index 0000000..f65d4a0 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b576cc230ba69b6c9d03f7fde0076cabd07906d0ee69a8695df279cbb017b78 +size 2545952800 diff --git a/gemma2-gutenberg-9B.i1-IQ1_S.gguf b/gemma2-gutenberg-9B.i1-IQ1_S.gguf new file mode 100644 index 0000000..ffc0ed6 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc1b3737549cff16d10d03a71498039321cecb76e262bae2a30736299f6d0d88 +size 2378565664 diff --git a/gemma2-gutenberg-9B.i1-IQ2_M.gguf b/gemma2-gutenberg-9B.i1-IQ2_M.gguf new file mode 100644 index 0000000..4541767 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7f1c440fcda8c2f19619a6d78039948da0f51aefa3460e0df5105b3b4714a4 +size 3434670112 diff --git a/gemma2-gutenberg-9B.i1-IQ2_S.gguf b/gemma2-gutenberg-9B.i1-IQ2_S.gguf new file mode 100644 index 0000000..9d3a1a1 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17475566d4283824f89a6c695b612c39df48386a91a90292d65802351a194d2 +size 3211487264 diff --git a/gemma2-gutenberg-9B.i1-IQ2_XS.gguf b/gemma2-gutenberg-9B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3e52616 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40bcaf5464dbe02aa5fa8f31cd6f03ef406be9cf84ea17f44369c210fa1f7a35 +size 3067381792 diff --git a/gemma2-gutenberg-9B.i1-IQ2_XXS.gguf b/gemma2-gutenberg-9B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..095face --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6118368e1a30778868e22892a571740f698ec13b92baf7034ebc8ea6fb0b308f +size 2824931360 diff --git a/gemma2-gutenberg-9B.i1-IQ3_M.gguf b/gemma2-gutenberg-9B.i1-IQ3_M.gguf new file mode 100644 index 0000000..4546a03 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d50071876c2f2488150c9af3fac9810f7ea1ea977a34a5b9846bb48d7bcb9a +size 4494616608 diff --git a/gemma2-gutenberg-9B.i1-IQ3_S.gguf b/gemma2-gutenberg-9B.i1-IQ3_S.gguf new file mode 100644 index 0000000..49582da --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9508a692e0f45b2aa33a78f01ca39192a68dba8e2eedc919889d068373d12c +size 4337666080 diff --git a/gemma2-gutenberg-9B.i1-IQ3_XS.gguf b/gemma2-gutenberg-9B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..f9dc02a --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9abd1983592492f43849d88eb6897e0eb806bcacdb372ecfea101a415bcb1a8e +size 4144990240 diff --git a/gemma2-gutenberg-9B.i1-IQ3_XXS.gguf b/gemma2-gutenberg-9B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ac4e45d --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c807cbffca94f17eaea3f28b060ec7b9cc0e71c498b617465bee43ad5e1fbb14 +size 3796740128 diff --git a/gemma2-gutenberg-9B.i1-IQ4_XS.gguf b/gemma2-gutenberg-9B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0f6251b --- /dev/null +++ b/gemma2-gutenberg-9B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9625c97939f312e5de75a272796a5653901aeb3650d08ef99ff74d360a319bb2 +size 5183031328 diff --git a/gemma2-gutenberg-9B.i1-Q2_K.gguf b/gemma2-gutenberg-9B.i1-Q2_K.gguf new file mode 100644 index 0000000..5258c77 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ec6a2ab60715e4c179b1a27c1b5909d277c0432177b4a1980fbf53d597d55f +size 3805399072 diff --git a/gemma2-gutenberg-9B.i1-Q3_K_L.gguf b/gemma2-gutenberg-9B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bfec56d --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21c3019eefddca5765e0a9ebaf9f41f3ebdb72afc5e8f5affcd9e95cdbb7c76c +size 5132453920 diff --git a/gemma2-gutenberg-9B.i1-Q3_K_M.gguf b/gemma2-gutenberg-9B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..e221073 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42fdf7117a0e20b3600f6c26583e2fa1f27273b6d986e4aefeb8bebb288f07a9 +size 4761782304 diff --git a/gemma2-gutenberg-9B.i1-Q3_K_S.gguf b/gemma2-gutenberg-9B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..010ea81 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eded710eafbe0523f590f952dec30e1afd4d28eada12d2f80a34917cff40208 +size 4337666080 diff --git a/gemma2-gutenberg-9B.i1-Q4_0.gguf b/gemma2-gutenberg-9B.i1-Q4_0.gguf new file mode 100644 index 0000000..9675a78 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3be4ee39cec8122ebec1e59e0f03de21a973649a683eaaf0f133e3061e2b7a9 +size 5459200032 diff --git a/gemma2-gutenberg-9B.i1-Q4_K_M.gguf b/gemma2-gutenberg-9B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f116085 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b0babc2942a0c32704b738a36853fd7cccce209463e56ad59cfda4b3cf439fc +size 5761058848 diff --git a/gemma2-gutenberg-9B.i1-Q4_K_S.gguf b/gemma2-gutenberg-9B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..14ac279 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f05acfc002d4406f352e6fdba76cb7fc6369cfbe731ac088b5a2efd2797ac9 +size 5478926368 diff --git a/gemma2-gutenberg-9B.i1-Q5_K_M.gguf b/gemma2-gutenberg-9B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..5021f86 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a3ea617801f1d9ca4979d8c220ab1e3de7e7a7cd781cf2cbe46603d521e9eb +size 6647367712 diff --git a/gemma2-gutenberg-9B.i1-Q5_K_S.gguf b/gemma2-gutenberg-9B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..f4ff3ba --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6de79f984f023c7daf90879913703a35420ef65bf5419c5763597da67482a261 +size 6483593248 diff --git a/gemma2-gutenberg-9B.i1-Q6_K.gguf b/gemma2-gutenberg-9B.i1-Q6_K.gguf new file mode 100644 index 0000000..c624d48 --- /dev/null +++ b/gemma2-gutenberg-9B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c804138ff1e63d6a6b243201d4a2a135100822467b15171cf80301f17e6c38 +size 7589070880 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..009eec9 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd3ceddcbf6c822c535b84c027f72008b37e717153f3eaecf4bc40b7ed1b56c5 +size 6116887