commit 75fb9b9686190161c029a7fc3ab79b9a6dc17d73 Author: ModelHub XC Date: Sun Oct 11 00:47:19 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bab29e1 --- /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 +EEVE-Korean-10.8B-v1.0.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +EEVE-Korean-10.8B-v1.0.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ1_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ1_M.gguf new file mode 100644 index 0000000..fd26e87 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ec0c132f89d603c579cb8c10247cafa40a5d3caee8da656f5807557f6a27da +size 2602234976 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ1_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ1_S.gguf new file mode 100644 index 0000000..0c2fc2d --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454f4efe409a02acc1b54b10b0548620ec5237df1b344788ed4f495de8ce77b9 +size 2388718688 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ2_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ2_M.gguf new file mode 100644 index 0000000..8daa3c5 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2d15d7f7d50d6601b37de6d11fba0265936d819524b1ccf9c02c601f54af410 +size 3718706272 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ2_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ2_S.gguf new file mode 100644 index 0000000..c91f796 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7017996e170af442df17380e1d50d9ef20e89d6e4eb541636edf8d783948db40 +size 3434017888 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ2_XS.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ2_XS.gguf new file mode 100644 index 0000000..c4c42f1 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdc2c8264e9c6486c680a30b307c45146adcda05da1a69cffa3f1c8a7fdb169b +size 3267949664 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ2_XXS.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1c2d8e7 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6613d5eb1cb8128ea5a2d9d5af4b58b50c57636a8aed0895b6759efb4159198 +size 2958095456 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ3_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ3_M.gguf new file mode 100644 index 0000000..48a1f98 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc97c66bff0b294a8cfebed89da7eff9a05efb88753f9436b20060e955f2cb7 +size 4891145312 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ3_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ3_S.gguf new file mode 100644 index 0000000..8a30ec5 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5aea8c1547ea27a196f88441e8e573fbc435e0e376d760009f0a32db73e46ad +size 4737397856 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ3_XS.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ3_XS.gguf new file mode 100644 index 0000000..94ac132 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e10ce31d99e108e819dc0f15acba35a1115a4dee5444c7b5dd5c7dbf4bacd66 +size 4492031072 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ3_XXS.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8855de1 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8dc95020a951572b9a5f25d02304b7cd1811e9926a9469c64d10de9311237127 +size 4208653408 diff --git a/EEVE-Korean-10.8B-v1.0.i1-IQ4_XS.gguf b/EEVE-Korean-10.8B-v1.0.i1-IQ4_XS.gguf new file mode 100644 index 0000000..7e9eb12 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fbf1bb406a1bf90945345c580f081d3083ac186fb68443f10320ecf762ad117 +size 5822411872 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q2_K.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q2_K.gguf new file mode 100644 index 0000000..3d48176 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2218885fc2a306b83e71c553d1b5aeb444f82b45ba6b9cf959c4e9990ce65707 +size 4045599840 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q3_K_L.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_L.gguf new file mode 100644 index 0000000..83cba65 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58bc4d601d06c07d14074456aa1b1a2cfa73c53ccc1e6a347f704e91a84cdcf4 +size 5696844896 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q3_K_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_M.gguf new file mode 100644 index 0000000..113cd89 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b7ac242fc9b8b4046e7b7d0edf1e8de17130ea0d3e6df39e1e1d67910838f0 +size 5241762912 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q3_K_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_S.gguf new file mode 100644 index 0000000..07c589d --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b1161a656374ef561070ff195ba884f59e097fd2e3e15380c28af0e3174ce7f +size 4710659168 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_0.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_0.gguf new file mode 100644 index 0000000..047d3f5 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f24e56bd9c265f55684621ccb49426581db4235ed0a94728901fb2b44d182e +size 6145373280 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_4.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..3318e0d --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eda449ac7290f145a13d8e4d29575b2622369ebec6d5c5890ba9b7474ce4ea9 +size 6123353184 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_8.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..a2fae80 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c42b3644bdb5f92bb1383c81ddf33b35ed9a717c7df58a6296663fd5181a8f0 +size 6123353184 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_0_8_8.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..09cfcf9 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c7f02c0381a330fcc359481d4ad9923a12977dad53a31274b448a1d7908767 +size 6123353184 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_K_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_K_M.gguf new file mode 100644 index 0000000..b175ac7 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:753bd3e43fc8d6ccd927a27a445638949cec519b6baaf9a6e5b127f6fc701997 +size 6512637024 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q4_K_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q4_K_S.gguf new file mode 100644 index 0000000..359a6d5 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a05d741771e557be143f866d2694b5d1619ea215475710443dd995ee21be6a +size 6169490528 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q5_K_M.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q5_K_M.gguf new file mode 100644 index 0000000..a7d2120 --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6676a2c758c422f6a78e499044ffdcbfdfadb891c9779a7dfbbaa50a6a0dfb7 +size 7653487712 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q5_K_S.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q5_K_S.gguf new file mode 100644 index 0000000..ccaed0f --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a176bd731e8e4f8f7a690b2609fb22ffda2f65bbb1121b085a9759dc434949c +size 7452947552 diff --git a/EEVE-Korean-10.8B-v1.0.i1-Q6_K.gguf b/EEVE-Korean-10.8B-v1.0.i1-Q6_K.gguf new file mode 100644 index 0000000..6252daa --- /dev/null +++ b/EEVE-Korean-10.8B-v1.0.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:300eba43130ffa972e517863371981db4580fb77931f985159c922f1b43504b1 +size 8865641568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..65a35b0 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: yanolja/YanoljaNEXT-EEVE-10.8B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/yanolja/YanoljaNEXT-EEVE-10.8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#EEVE-Korean-10.8B-v1.0-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-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/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ2_S.gguf) | i1-IQ2_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ2_M.gguf) | i1-IQ2_M | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q2_K.gguf) | i1-Q2_K | 4.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 4.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ3_S.gguf) | i1-IQ3_S | 4.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ3_M.gguf) | i1-IQ3_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q3_K_M.gguf) | i1-Q3_K_M | 5.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 6.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 6.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 6.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_0.gguf) | i1-Q4_0 | 6.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_K_S.gguf) | i1-Q4_K_S | 6.3 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q4_K_M.gguf) | i1-Q4_K_M | 6.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q5_K_S.gguf) | i1-Q5_K_S | 7.6 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q5_K_M.gguf) | i1-Q5_K_M | 7.8 | | +| [GGUF](https://huggingface.co/mradermacher/EEVE-Korean-10.8B-v1.0-i1-GGUF/resolve/main/EEVE-Korean-10.8B-v1.0.i1-Q6_K.gguf) | i1-Q6_K | 9.0 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..662deb3 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ee3158963b79c57910c9ee40dabaae36c9d258955c0b063aeacf3a4500ee76 +size 7482253