commit c5dfe4004eed56ed77f60f2e90b0350e50ece9bb Author: ModelHub XC Date: Sun Oct 18 05:15:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Saka-7.6B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..93e2abb --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Saka-7.6B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2ddaccc --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: Sakalti/Saka-7.6B +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/Sakalti/Saka-7.6B + + +static quants are available at https://huggingface.co/mradermacher/Saka-7.6B-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/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Saka-7.6B-i1-GGUF/resolve/main/Saka-7.6B.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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/Saka-7.6B.i1-IQ1_M.gguf b/Saka-7.6B.i1-IQ1_M.gguf new file mode 100644 index 0000000..b3cf6bc --- /dev/null +++ b/Saka-7.6B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e682072f8f543651531f27297c6cd4108355f2e62d149b9dbb1e370db164b1a +size 2042197248 diff --git a/Saka-7.6B.i1-IQ1_S.gguf b/Saka-7.6B.i1-IQ1_S.gguf new file mode 100644 index 0000000..fb3b37e --- /dev/null +++ b/Saka-7.6B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0fcb139104c1c4fa2f611ae4c88f3f17d5efb90f95e4e6323a302cb26141ffa +size 1903668480 diff --git a/Saka-7.6B.i1-IQ2_M.gguf b/Saka-7.6B.i1-IQ2_M.gguf new file mode 100644 index 0000000..48585e6 --- /dev/null +++ b/Saka-7.6B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e0460bb5e19b79f0295515c8ee9003ddb15e8ed66fb2ff50681bf5d2a2aecb +size 2780343552 diff --git a/Saka-7.6B.i1-IQ2_S.gguf b/Saka-7.6B.i1-IQ2_S.gguf new file mode 100644 index 0000000..78df1da --- /dev/null +++ b/Saka-7.6B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d75c1289bf38297b6dfbdf88b11417633d9c1d744d798bdf90cc50470518ad8f +size 2595638528 diff --git a/Saka-7.6B.i1-IQ2_XS.gguf b/Saka-7.6B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a08d055 --- /dev/null +++ b/Saka-7.6B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a06d48f20695d4c5fa85b86fb1797cae9a70199a76d6cc2a8182a06e7ebe7e9 +size 2469022976 diff --git a/Saka-7.6B.i1-IQ2_XXS.gguf b/Saka-7.6B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a7559b0 --- /dev/null +++ b/Saka-7.6B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2425428b60e297ad16da39601c9b4cff040812f76e390f62c5ec5d2af70acf98 +size 2273078528 diff --git a/Saka-7.6B.i1-IQ3_M.gguf b/Saka-7.6B.i1-IQ3_M.gguf new file mode 100644 index 0000000..17980a7 --- /dev/null +++ b/Saka-7.6B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf77ad25f4b843079bde135c670c93a3467b12c2126c0b26dc13ddd6d53bf5b +size 3574013184 diff --git a/Saka-7.6B.i1-IQ3_S.gguf b/Saka-7.6B.i1-IQ3_S.gguf new file mode 100644 index 0000000..5de5080 --- /dev/null +++ b/Saka-7.6B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a6ab6cc1d6c0dd278f1fa9d1df58e39210ed99ccfebf7947362b7dea9429362 +size 3499193600 diff --git a/Saka-7.6B.i1-IQ3_XS.gguf b/Saka-7.6B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..651774f --- /dev/null +++ b/Saka-7.6B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf43aa34148a7e3d06f9435c1999cb9157740d3e32235614e113fcb4880222ea +size 3346257152 diff --git a/Saka-7.6B.i1-IQ3_XXS.gguf b/Saka-7.6B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ac6642d --- /dev/null +++ b/Saka-7.6B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9803d0b56c2210b7dd393fb34d1a2240594669425363d4a660ccbebd56046e8e +size 3114515712 diff --git a/Saka-7.6B.i1-IQ4_NL.gguf b/Saka-7.6B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..e2e7a14 --- /dev/null +++ b/Saka-7.6B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91a3c20d85573a17271576b283e3c2c5b741324b1b522990f9ac15677b37cf2a +size 4437814528 diff --git a/Saka-7.6B.i1-IQ4_XS.gguf b/Saka-7.6B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..9b45d42 --- /dev/null +++ b/Saka-7.6B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182f20d2f982e21fce784f280857499c688c11b8be64767847be82f5dbf174c6 +size 4218473728 diff --git a/Saka-7.6B.i1-Q2_K.gguf b/Saka-7.6B.i1-Q2_K.gguf new file mode 100644 index 0000000..47fae53 --- /dev/null +++ b/Saka-7.6B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2133267b73758271926d75ec03d2c6e836c6caaf6654aedb550c09ab07a2c31c +size 3015941376 diff --git a/Saka-7.6B.i1-Q2_K_S.gguf b/Saka-7.6B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..d96878e --- /dev/null +++ b/Saka-7.6B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cad90ca4b1d71ed9bdbd3de7ab7e36fd923f405882070c875588a163a07f3ba2 +size 2834074880 diff --git a/Saka-7.6B.i1-Q3_K_L.gguf b/Saka-7.6B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0760789 --- /dev/null +++ b/Saka-7.6B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f9709cc93385d107c2f0376c678581f5b15dab5ad4a6a57a2088b61c555998d +size 4088460544 diff --git a/Saka-7.6B.i1-Q3_K_M.gguf b/Saka-7.6B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..49a1d2c --- /dev/null +++ b/Saka-7.6B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5f8c3c14f7f487ddac48c0bdeb66e99e2459d47978295cd5d693a1ce3b1c0e +size 3808392448 diff --git a/Saka-7.6B.i1-Q3_K_S.gguf b/Saka-7.6B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..68290ef --- /dev/null +++ b/Saka-7.6B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9f90c80277e116a49de00851d8b421df9f5df98021da11c2086dcd98f916b2 +size 3492369664 diff --git a/Saka-7.6B.i1-Q4_0.gguf b/Saka-7.6B.i1-Q4_0.gguf new file mode 100644 index 0000000..43983c3 --- /dev/null +++ b/Saka-7.6B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b9e17ec9b7e6b57f474c68a947dc1d390015d1558d4c7c51d8c00bd616241d +size 4444122368 diff --git a/Saka-7.6B.i1-Q4_1.gguf b/Saka-7.6B.i1-Q4_1.gguf new file mode 100644 index 0000000..7060f57 --- /dev/null +++ b/Saka-7.6B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0fe347d4f6698aa516b09ab9be6c3cba968f15dd153f7e466b757fe5aa020e9 +size 4873284864 diff --git a/Saka-7.6B.i1-Q4_K_M.gguf b/Saka-7.6B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9ca3b67 --- /dev/null +++ b/Saka-7.6B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f2ff6c7843fdca5062dbbc5cc1568cf63067fcda2fc5eb166ea7a3df26ed0e +size 4683074816 diff --git a/Saka-7.6B.i1-Q4_K_S.gguf b/Saka-7.6B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b6ca96b --- /dev/null +++ b/Saka-7.6B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97f39bc4c8571ce9a50472b38dfb6131750f5ed467ba0bc8c989a848acf9efb +size 4457770240 diff --git a/Saka-7.6B.i1-Q5_K_M.gguf b/Saka-7.6B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..99c31e5 --- /dev/null +++ b/Saka-7.6B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc0b2fdb92820325414fbd65b7b9d656b56ccd8f087f9407a3bd3aa196a3544 +size 5444832512 diff --git a/Saka-7.6B.i1-Q5_K_S.gguf b/Saka-7.6B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..3907546 --- /dev/null +++ b/Saka-7.6B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd6bdcefd7e51be787e9dec2672a19abac375220477c5e2e84de6f6e6f870a05 +size 5315177728 diff --git a/Saka-7.6B.i1-Q6_K.gguf b/Saka-7.6B.i1-Q6_K.gguf new file mode 100644 index 0000000..00e65ad --- /dev/null +++ b/Saka-7.6B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e90e50f033cd7d4908c5d5eadacd14a22f0ffeefcb3506a9aae22eb4bdaf15c +size 6254200064 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..0c25f7c --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e9ec5f9bdeaa8e4ff91d53646871015ed3836cff4837a28893fc2dc3d9bb25 +size 4536665