commit 907f495b30da8361ae7913e58cdbb66d7f601bd2 Author: ModelHub XC Date: Wed May 6 21:15:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenCoder-8B-Base-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..25b25d8 --- /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 +OpenCoder-8B-Base.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +OpenCoder-8B-Base.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenCoder-8B-Base.i1-IQ1_M.gguf b/OpenCoder-8B-Base.i1-IQ1_M.gguf new file mode 100644 index 0000000..5ecef92 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c9db9e9aa424b11eaf492b2bf47074cac37ea45b3f5f7f12bbf4b51519815d5 +size 2024847168 diff --git a/OpenCoder-8B-Base.i1-IQ1_S.gguf b/OpenCoder-8B-Base.i1-IQ1_S.gguf new file mode 100644 index 0000000..86c4f14 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3db03e85f03c1503f9bff47a5a322a2bb624af75d4092274f57f0cb459581b8 +size 1882502976 diff --git a/OpenCoder-8B-Base.i1-IQ2_M.gguf b/OpenCoder-8B-Base.i1-IQ2_M.gguf new file mode 100644 index 0000000..aef0995 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be4e391e6768a939569533da16501e368b4f6e86420da270968ad2fa0eb9238c +size 2798004032 diff --git a/OpenCoder-8B-Base.i1-IQ2_S.gguf b/OpenCoder-8B-Base.i1-IQ2_S.gguf new file mode 100644 index 0000000..50e5bb0 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae97434327a8ab7ea30c934f214db115cbe64c897ef579d97dc845bc2d9a1d2 +size 2608211776 diff --git a/OpenCoder-8B-Base.i1-IQ2_XS.gguf b/OpenCoder-8B-Base.i1-IQ2_XS.gguf new file mode 100644 index 0000000..bb56d7a --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3052533f516d673e6d339bc9609042ad5d4a22ab270fd1e88677b62251c5366 +size 2468656960 diff --git a/OpenCoder-8B-Base.i1-IQ2_XXS.gguf b/OpenCoder-8B-Base.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..0810ddc --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c733a769b82f7853234893f4ba87239123e12adff6b965143c4f98b60b78ca6 +size 2262087488 diff --git a/OpenCoder-8B-Base.i1-IQ3_M.gguf b/OpenCoder-8B-Base.i1-IQ3_M.gguf new file mode 100644 index 0000000..99c021c --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd082d4d1d8fc7b32b12cb4018731d9710246452795e3fbe44013b8fc8deb98 +size 3617347392 diff --git a/OpenCoder-8B-Base.i1-IQ3_S.gguf b/OpenCoder-8B-Base.i1-IQ3_S.gguf new file mode 100644 index 0000000..fa3ca62 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:500f0cbe21827b037c59f426f98a822fdf1a1085a9941804149cf7a21f5c6b98 +size 3514849088 diff --git a/OpenCoder-8B-Base.i1-IQ3_XS.gguf b/OpenCoder-8B-Base.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d10d7ee --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f9084c631fa4639bd1b5b5d4c45013731f46afa01d64e874c1f9709cc9eeeb6 +size 3351271232 diff --git a/OpenCoder-8B-Base.i1-IQ3_XXS.gguf b/OpenCoder-8B-Base.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5f8a356 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:728c833ba4d8d1cea513e354ed950d74ed7197d14b6d8826d7e54b91799ba4b6 +size 3124635456 diff --git a/OpenCoder-8B-Base.i1-IQ4_XS.gguf b/OpenCoder-8B-Base.i1-IQ4_XS.gguf new file mode 100644 index 0000000..67ba996 --- /dev/null +++ b/OpenCoder-8B-Base.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e17c438ce2f7b649cfa305e39afe69e360d53ec86ca960d22f52da40142a7984 +size 4267034432 diff --git a/OpenCoder-8B-Base.i1-Q2_K.gguf b/OpenCoder-8B-Base.i1-Q2_K.gguf new file mode 100644 index 0000000..66fc0fa --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed8be369fb33a21a047c317aa841e0805e61205159a7a02e05790530b27a2cb7 +size 3024807744 diff --git a/OpenCoder-8B-Base.i1-Q3_K_L.gguf b/OpenCoder-8B-Base.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5f9bf11 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7acdbce8309cfc884196f4c3aca1692c2e490154b82d5dbf3ff67bfb1d6424bb +size 4154480448 diff --git a/OpenCoder-8B-Base.i1-Q3_K_M.gguf b/OpenCoder-8B-Base.i1-Q3_K_M.gguf new file mode 100644 index 0000000..f057196 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88de740f3fa1f01428c5048bde0b93826576b3c7138e4579678b71d10fdf735b +size 3851441984 diff --git a/OpenCoder-8B-Base.i1-Q3_K_S.gguf b/OpenCoder-8B-Base.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d171b97 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8f841a4fc8984d65add7673303bb31eeae704ec6d0fda506fccfd111349ede4 +size 3497023296 diff --git a/OpenCoder-8B-Base.i1-Q4_0.gguf b/OpenCoder-8B-Base.i1-Q4_0.gguf new file mode 100644 index 0000000..4841258 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc0a60405f15b757f67e289cfaa7fee439c10004b39ba320ff7a6ec1b1abdce +size 4491216704 diff --git a/OpenCoder-8B-Base.i1-Q4_0_4_4.gguf b/OpenCoder-8B-Base.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..0d6643d --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3995e87c275e0b4d4d4ce17130f66030d941ca786019d5222e3da07f2c2e5494 +size 4476536640 diff --git a/OpenCoder-8B-Base.i1-Q4_0_4_8.gguf b/OpenCoder-8B-Base.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..a2d67be --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd070f0e613dfa48fd860d9223de302871f6c4084c569990ae712e72a1b710a +size 4476536640 diff --git a/OpenCoder-8B-Base.i1-Q4_0_8_8.gguf b/OpenCoder-8B-Base.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..2f03c91 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ed19a8715effb6b3e8e51f3109f6f257c41e44b4d80efce605a4381c522143 +size 4476536640 diff --git a/OpenCoder-8B-Base.i1-Q4_K_M.gguf b/OpenCoder-8B-Base.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f81bcb9 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6600254cd58b505c5e9863a4c7fee84a601889d05e44cee7868cd0b9dc84f84e +size 4736059200 diff --git a/OpenCoder-8B-Base.i1-Q4_K_S.gguf b/OpenCoder-8B-Base.i1-Q4_K_S.gguf new file mode 100644 index 0000000..b3dbb90 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82e418331ec397807c67d46d03011990450c1ab74f56128358dbdbd326283d8f +size 4507993920 diff --git a/OpenCoder-8B-Base.i1-Q5_K_M.gguf b/OpenCoder-8B-Base.i1-Q5_K_M.gguf new file mode 100644 index 0000000..c7d1e86 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0db6c78b2fe0c2609f8fc1755e9fd7d2ee84d34ee39733cc23ae009ca74ad955 +size 5532124992 diff --git a/OpenCoder-8B-Base.i1-Q5_K_S.gguf b/OpenCoder-8B-Base.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8848847 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:423402f0a308525f1207d47593322a78b290929e538951c1c847e388298eb8c5 +size 5398431552 diff --git a/OpenCoder-8B-Base.i1-Q6_K.gguf b/OpenCoder-8B-Base.i1-Q6_K.gguf new file mode 100644 index 0000000..ff3edd2 --- /dev/null +++ b/OpenCoder-8B-Base.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:882f6a6bae5ecc128db8b312a3642bcf79e7f7a55db9143bdaf4bc69a6d438ef +size 6377944896 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dabbe90 --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: infly/OpenCoder-8B-Base +language: +- en +- zh +library_name: transformers +license: other +license_link: https://huggingface.co/infly/OpenCoder-8B-Base/blob/main/LICENSE +license_name: inf +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/infly/OpenCoder-8B-Base + + +static quants are available at https://huggingface.co/mradermacher/OpenCoder-8B-Base-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/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.6 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.6 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.6 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_0.gguf) | i1-Q4_0 | 4.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenCoder-8B-Base-i1-GGUF/resolve/main/OpenCoder-8B-Base.i1-Q6_K.gguf) | i1-Q6_K | 6.5 | 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..3423601 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a200a7714926594c3a9be5ac35d8b91b1de166cb02c7cbda192a32cabf7e2f +size 4988157