commit 7e9902dac415fd5c83d8f4a5dccf555be9f1dc8d Author: ModelHub XC Date: Mon May 11 10:36:05 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Arisu-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7719fc1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Arisu-12B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Arisu-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Arisu-12B.i1-IQ1_M.gguf b/Arisu-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..a5770bb --- /dev/null +++ b/Arisu-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741c7ea57cd5fa1f539f53d539b93f6804187c3e0f296c1334308379f1a0fd68 +size 3221624992 diff --git a/Arisu-12B.i1-IQ1_S.gguf b/Arisu-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..7deb62b --- /dev/null +++ b/Arisu-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aef66b2386e483fab45d4f8ec308ddb8e5449c872ff20d16d25750125c493c2 +size 2999212192 diff --git a/Arisu-12B.i1-IQ2_M.gguf b/Arisu-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..12e2872 --- /dev/null +++ b/Arisu-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e77667fef664da7c235d71e06749128b2a9eb7822e0fe11cd5263ed7b68000 +size 4435024032 diff --git a/Arisu-12B.i1-IQ2_S.gguf b/Arisu-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c469c39 --- /dev/null +++ b/Arisu-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b95fd74b8f3bd6ae4f716b5d2be12dd82d1f7a64300121cc9b6ce2755d0a1fef +size 4138473632 diff --git a/Arisu-12B.i1-IQ2_XS.gguf b/Arisu-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..04d7fd5 --- /dev/null +++ b/Arisu-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c7d085d98833e54fa2af818acb9cc9ecd479b3d47a9146527bedf4073796a73 +size 3915077792 diff --git a/Arisu-12B.i1-IQ2_XXS.gguf b/Arisu-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..58f5381 --- /dev/null +++ b/Arisu-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ded1e484d95eb8ad182291507ebaa27603c65eeffb745c13a0305446e39b6f5 +size 3592312992 diff --git a/Arisu-12B.i1-IQ3_M.gguf b/Arisu-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..b7b913c --- /dev/null +++ b/Arisu-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:903f9c087bdcb1ec4370d47d85ea21bdec57231fe18d3de1008a8378bd3acf8a +size 5722232992 diff --git a/Arisu-12B.i1-IQ3_S.gguf b/Arisu-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..ec6394a --- /dev/null +++ b/Arisu-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf2eee3d09fd1a554c91934201031837728269b9b914e4f498e94dd2cb289ec5 +size 5562079392 diff --git a/Arisu-12B.i1-IQ3_XS.gguf b/Arisu-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..ce764e9 --- /dev/null +++ b/Arisu-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca2d4063042d2a70301ae841ebb3ed47a2c5eef666c607d1adb7478155bd4ede +size 5306488992 diff --git a/Arisu-12B.i1-IQ3_XXS.gguf b/Arisu-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..fc85a5a --- /dev/null +++ b/Arisu-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905d715833a04ffc901f518a14b2fa2b358d5d5fc0a4cb7d413a0e98250bf847 +size 4945385632 diff --git a/Arisu-12B.i1-IQ4_NL.gguf b/Arisu-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..ca9a1de --- /dev/null +++ b/Arisu-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9f0e9486c541ef2bb74dc00d49edab95286c4710d88ce5fac44fbf078efadca +size 7097915552 diff --git a/Arisu-12B.i1-IQ4_XS.gguf b/Arisu-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..3fff104 --- /dev/null +++ b/Arisu-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a15d2ed86cd3315509e9333160e9b2ed14c41b8da754b5e5d2777b6d3041c8a +size 6742710432 diff --git a/Arisu-12B.i1-Q2_K.gguf b/Arisu-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..0cddcfc --- /dev/null +++ b/Arisu-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e8c6dd2216edcde6cab46887024fb4cea7dac6e6a57e977bce29993b4ad0bf4 +size 4791048352 diff --git a/Arisu-12B.i1-Q2_K_S.gguf b/Arisu-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..4d56925 --- /dev/null +++ b/Arisu-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177cc86e7bb66143e290fdc757146062c0e463a2dd8c31cc69095da4be27d753 +size 4493678752 diff --git a/Arisu-12B.i1-Q3_K_L.gguf b/Arisu-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..614eab1 --- /dev/null +++ b/Arisu-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:108418b6b288ca40a5c7d83a033e263cbc67197b3c30d22dc594114f22540aed +size 6561503392 diff --git a/Arisu-12B.i1-Q3_K_M.gguf b/Arisu-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..4a78bcc --- /dev/null +++ b/Arisu-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f5ed27a482f25a3452ed0b0766366f0b2bc7e5b43ebb2c90c655b09d15f796 +size 6083090592 diff --git a/Arisu-12B.i1-Q3_K_S.gguf b/Arisu-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..2a4d224 --- /dev/null +++ b/Arisu-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76c6052b84ca7a918cb3473f1676a1518dbf5a02fd62d24d4acc1eaed45894ec +size 5534226592 diff --git a/Arisu-12B.i1-Q4_0.gguf b/Arisu-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..131ee47 --- /dev/null +++ b/Arisu-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9208e36d0842828d2e21623273a70d65ad9a772eccc6c98bdbf5747f397bfc11 +size 7094638752 diff --git a/Arisu-12B.i1-Q4_1.gguf b/Arisu-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..082bcfd --- /dev/null +++ b/Arisu-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26e890910b6c47524429527f684f4b7c166209da79efdb6bc61fcb0f8e87fc0 +size 7795218592 diff --git a/Arisu-12B.i1-Q4_K_M.gguf b/Arisu-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0b61846 --- /dev/null +++ b/Arisu-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c0ce7846da6ec9fda4175d8cfdacdbac9c7e025b67a74d40e4000f8658a3805 +size 7477205152 diff --git a/Arisu-12B.i1-Q4_K_S.gguf b/Arisu-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..abc49b1 --- /dev/null +++ b/Arisu-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:669d5b9a74f16061fa67d62ec0219f2f466f29bdaed9c17b9b2f67f5f5ad3ff5 +size 7120197792 diff --git a/Arisu-12B.i1-Q5_K_M.gguf b/Arisu-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..6d41b82 --- /dev/null +++ b/Arisu-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5164f2f12ca85f47ee457861bdebaaa7ae3a5cadb8421448fef1e29bdaae0a +size 8727632032 diff --git a/Arisu-12B.i1-Q5_K_S.gguf b/Arisu-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9ee0bd4 --- /dev/null +++ b/Arisu-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4787afea094e136efd222d29bda1859ed4584fc115a0bcb9e4493566660cb2bb +size 8518736032 diff --git a/Arisu-12B.i1-Q6_K.gguf b/Arisu-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..36611d4 --- /dev/null +++ b/Arisu-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5881be96d7a976cd8d434acd75c76966ee51a946c862444a8d294a0a65ff95e5 +size 10056210592 diff --git a/Arisu-12B.imatrix.gguf b/Arisu-12B.imatrix.gguf new file mode 100644 index 0000000..e5c58a9 --- /dev/null +++ b/Arisu-12B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1a2ad864c61177856538bfc1498d1ff9fc58363fdb1d66b7954efe6bca5ad97 +size 7088192 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdf8f5d --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: mergekit-community/Arisu-12B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/mergekit-community/Arisu-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Arisu-12B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Arisu-12B-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/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Arisu-12B-i1-GGUF/resolve/main/Arisu-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | 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. + +