From 61e5192360792eb210d676366d5b8bc9e523c77d Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Tue, 5 May 2026 08:41:45 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: mradermacher/arctune-gpt20b-i1-GGUF Source: Original Platform --- .gitattributes | 60 +++++++++++++++++++++ README.md | 89 ++++++++++++++++++++++++++++++++ arctune-gpt20b.i1-IQ1_M.gguf | 3 ++ arctune-gpt20b.i1-IQ1_S.gguf | 3 ++ arctune-gpt20b.i1-IQ2_M.gguf | 3 ++ arctune-gpt20b.i1-IQ2_S.gguf | 3 ++ arctune-gpt20b.i1-IQ2_XS.gguf | 3 ++ arctune-gpt20b.i1-IQ2_XXS.gguf | 3 ++ arctune-gpt20b.i1-IQ3_M.gguf | 3 ++ arctune-gpt20b.i1-IQ3_S.gguf | 3 ++ arctune-gpt20b.i1-IQ3_XS.gguf | 3 ++ arctune-gpt20b.i1-IQ3_XXS.gguf | 3 ++ arctune-gpt20b.i1-IQ4_XS.gguf | 3 ++ arctune-gpt20b.i1-MXFP4_MOE.gguf | 3 ++ arctune-gpt20b.i1-Q2_K.gguf | 3 ++ arctune-gpt20b.i1-Q2_K_S.gguf | 3 ++ arctune-gpt20b.i1-Q3_K_L.gguf | 3 ++ arctune-gpt20b.i1-Q3_K_M.gguf | 3 ++ arctune-gpt20b.i1-Q3_K_S.gguf | 3 ++ arctune-gpt20b.i1-Q4_0.gguf | 3 ++ arctune-gpt20b.i1-Q4_1.gguf | 3 ++ arctune-gpt20b.i1-Q4_K_M.gguf | 3 ++ arctune-gpt20b.i1-Q4_K_S.gguf | 3 ++ arctune-gpt20b.i1-Q5_K_M.gguf | 3 ++ arctune-gpt20b.i1-Q5_K_S.gguf | 3 ++ arctune-gpt20b.i1-Q6_K.gguf | 3 ++ arctune-gpt20b.imatrix.gguf | 3 ++ 27 files changed, 224 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 arctune-gpt20b.i1-IQ1_M.gguf create mode 100644 arctune-gpt20b.i1-IQ1_S.gguf create mode 100644 arctune-gpt20b.i1-IQ2_M.gguf create mode 100644 arctune-gpt20b.i1-IQ2_S.gguf create mode 100644 arctune-gpt20b.i1-IQ2_XS.gguf create mode 100644 arctune-gpt20b.i1-IQ2_XXS.gguf create mode 100644 arctune-gpt20b.i1-IQ3_M.gguf create mode 100644 arctune-gpt20b.i1-IQ3_S.gguf create mode 100644 arctune-gpt20b.i1-IQ3_XS.gguf create mode 100644 arctune-gpt20b.i1-IQ3_XXS.gguf create mode 100644 arctune-gpt20b.i1-IQ4_XS.gguf create mode 100644 arctune-gpt20b.i1-MXFP4_MOE.gguf create mode 100644 arctune-gpt20b.i1-Q2_K.gguf create mode 100644 arctune-gpt20b.i1-Q2_K_S.gguf create mode 100644 arctune-gpt20b.i1-Q3_K_L.gguf create mode 100644 arctune-gpt20b.i1-Q3_K_M.gguf create mode 100644 arctune-gpt20b.i1-Q3_K_S.gguf create mode 100644 arctune-gpt20b.i1-Q4_0.gguf create mode 100644 arctune-gpt20b.i1-Q4_1.gguf create mode 100644 arctune-gpt20b.i1-Q4_K_M.gguf create mode 100644 arctune-gpt20b.i1-Q4_K_S.gguf create mode 100644 arctune-gpt20b.i1-Q5_K_M.gguf create mode 100644 arctune-gpt20b.i1-Q5_K_S.gguf create mode 100644 arctune-gpt20b.i1-Q6_K.gguf create mode 100644 arctune-gpt20b.imatrix.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..87a5ef9 --- /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 +arctune-gpt20b.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-MXFP4_MOE.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +arctune-gpt20b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..27c35c7 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: EpistemeAI/arctune-gpt20b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- gpt_oss +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/EpistemeAI/arctune-gpt20b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#arctune-gpt20b-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/arctune-gpt20b-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/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ1_M.gguf) | i1-IQ1_M | 12.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ1_S.gguf) | i1-IQ1_S | 12.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 12.1 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 12.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ2_M.gguf) | i1-IQ2_M | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ2_S.gguf) | i1-IQ2_S | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ3_S.gguf) | i1-IQ3_S | 12.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q2_K.gguf) | i1-Q2_K | 12.2 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 12.2 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 12.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q4_0.gguf) | i1-Q4_0 | 12.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-IQ3_M.gguf) | i1-IQ3_M | 12.3 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 13.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 13.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q4_1.gguf) | i1-Q4_1 | 13.5 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 14.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 15.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 16.0 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 17.0 | | +| [GGUF](https://huggingface.co/mradermacher/arctune-gpt20b-i1-GGUF/resolve/main/arctune-gpt20b.i1-Q6_K.gguf) | i1-Q6_K | 22.3 | 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/arctune-gpt20b.i1-IQ1_M.gguf b/arctune-gpt20b.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a3eb38 --- /dev/null +++ b/arctune-gpt20b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9cbdc773394f9f68da9d4f5c6a6d3fe3c287005c13e41dd91b8b703479e3d14 +size 12016852960 diff --git a/arctune-gpt20b.i1-IQ1_S.gguf b/arctune-gpt20b.i1-IQ1_S.gguf new file mode 100644 index 0000000..496c2b5 --- /dev/null +++ b/arctune-gpt20b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31cb857dc9c26d74e0ffaa9a183f13030adc1c72388d094f6eb8667b8fe4fdce +size 12016852960 diff --git a/arctune-gpt20b.i1-IQ2_M.gguf b/arctune-gpt20b.i1-IQ2_M.gguf new file mode 100644 index 0000000..9e3a1f2 --- /dev/null +++ b/arctune-gpt20b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccd4cf76c4b7dc26f234c3e98ec8f97dd6f6e374655ce80b71d37c19ca850605 +size 12065513440 diff --git a/arctune-gpt20b.i1-IQ2_S.gguf b/arctune-gpt20b.i1-IQ2_S.gguf new file mode 100644 index 0000000..fa4ccc6 --- /dev/null +++ b/arctune-gpt20b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3326cce65a18add447fe32d4d88381863612eeb94bfae14dbe37a8a7af98f35 +size 12065513440 diff --git a/arctune-gpt20b.i1-IQ2_XS.gguf b/arctune-gpt20b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..a817981 --- /dev/null +++ b/arctune-gpt20b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810d2733afcc506fdf55442f8c8252ae9ed94cf08249af6624643c2c599307c5 +size 12025700320 diff --git a/arctune-gpt20b.i1-IQ2_XXS.gguf b/arctune-gpt20b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..aa5f9cc --- /dev/null +++ b/arctune-gpt20b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b34cbbb9bb510bf5394e77cf0d08cdeaf2a9abd446373a719a9e19ede61e3bbc +size 12016852960 diff --git a/arctune-gpt20b.i1-IQ3_M.gguf b/arctune-gpt20b.i1-IQ3_M.gguf new file mode 100644 index 0000000..4c5ca14 --- /dev/null +++ b/arctune-gpt20b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:284642ab67f7a7ffbc445b50e368312c1c73bc2670fbee3ff7ca8277942029ac +size 12202647520 diff --git a/arctune-gpt20b.i1-IQ3_S.gguf b/arctune-gpt20b.i1-IQ3_S.gguf new file mode 100644 index 0000000..aaee537 --- /dev/null +++ b/arctune-gpt20b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d695543815160be4bd2ab081d1375e767d48545d9be32e68e2c8afe615872a4a +size 12065513440 diff --git a/arctune-gpt20b.i1-IQ3_XS.gguf b/arctune-gpt20b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..7f8ad57 --- /dev/null +++ b/arctune-gpt20b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5726db6e2d38f589487a53b41896fc9b61086c8719099508755e5446239f1cc3 +size 12065513440 diff --git a/arctune-gpt20b.i1-IQ3_XXS.gguf b/arctune-gpt20b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..f9ac550 --- /dev/null +++ b/arctune-gpt20b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d8517e4743c18bf9a4cc1c9829ad9c717606006c8b36cdea1b9c6535dae1c5 +size 12065513440 diff --git a/arctune-gpt20b.i1-IQ4_XS.gguf b/arctune-gpt20b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..0af36d5 --- /dev/null +++ b/arctune-gpt20b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f617d7bb2d0f77eab4aab5000e2be65a6ff075cb30bd2206898c875a6a46dc7 +size 12096479200 diff --git a/arctune-gpt20b.i1-MXFP4_MOE.gguf b/arctune-gpt20b.i1-MXFP4_MOE.gguf new file mode 100644 index 0000000..5942147 --- /dev/null +++ b/arctune-gpt20b.i1-MXFP4_MOE.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10772be700b957871c90592034e0b2c67c871ed40bb8fa63b68318f87330cbf5 +size 12109565920 diff --git a/arctune-gpt20b.i1-Q2_K.gguf b/arctune-gpt20b.i1-Q2_K.gguf new file mode 100644 index 0000000..864c3f3 --- /dev/null +++ b/arctune-gpt20b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379091d4fc516eb9fb7e5a7e5c1d17f7efc5b0e55bd771d3c10ca9cfc2908e31 +size 12065513440 diff --git a/arctune-gpt20b.i1-Q2_K_S.gguf b/arctune-gpt20b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f64b65e --- /dev/null +++ b/arctune-gpt20b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5d36604b7c0828f8f0cf026294f5e55b6f1ce963fdbd0d7b2253744e4a19687 +size 12136292320 diff --git a/arctune-gpt20b.i1-Q3_K_L.gguf b/arctune-gpt20b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..5e37e35 --- /dev/null +++ b/arctune-gpt20b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83f8bee0d208dd6765ffdaf2eee50c8856048a2dd84e450d182cc377af3c595a +size 13335109600 diff --git a/arctune-gpt20b.i1-Q3_K_M.gguf b/arctune-gpt20b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a2d77ea --- /dev/null +++ b/arctune-gpt20b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238664ff01c207b65337fe89096e44fda1961b593c8b23af5c838f04123ee34b +size 12916150240 diff --git a/arctune-gpt20b.i1-Q3_K_S.gguf b/arctune-gpt20b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..93d668b --- /dev/null +++ b/arctune-gpt20b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a83728b565a6508d2578deec509b00497b5c014996d6fab7921686d1c753a5 +size 12061089760 diff --git a/arctune-gpt20b.i1-Q4_0.gguf b/arctune-gpt20b.i1-Q4_0.gguf new file mode 100644 index 0000000..267838e --- /dev/null +++ b/arctune-gpt20b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:847c67db13c6d2adf8e51cca34a73f56de0093fa532fcd997de8372411c8ae25 +size 12148457440 diff --git a/arctune-gpt20b.i1-Q4_1.gguf b/arctune-gpt20b.i1-Q4_1.gguf new file mode 100644 index 0000000..56e0166 --- /dev/null +++ b/arctune-gpt20b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a035b4816ba9f763a2ae3cef3f6ba4969e90606c0d0692c6927297266d141a +size 13369093600 diff --git a/arctune-gpt20b.i1-Q4_K_M.gguf b/arctune-gpt20b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..9d2b96a --- /dev/null +++ b/arctune-gpt20b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c71e3ba408a2ae6db9af2c57da9830f8072ecd06511f9975cd21c702b275d2 +size 15805135840 diff --git a/arctune-gpt20b.i1-Q4_K_S.gguf b/arctune-gpt20b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4a74695 --- /dev/null +++ b/arctune-gpt20b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b36a966ef2bc27387f04252a322341b5a81e0c5cf211c85f6cd8f0f04fbed9a +size 14654241760 diff --git a/arctune-gpt20b.i1-Q5_K_M.gguf b/arctune-gpt20b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e25a1c9 --- /dev/null +++ b/arctune-gpt20b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f478a1b17959565a56fff1709e86b9a7847de6281b06bf14900d062b37047bbb +size 16893061600 diff --git a/arctune-gpt20b.i1-Q5_K_S.gguf b/arctune-gpt20b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7004c72 --- /dev/null +++ b/arctune-gpt20b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f234ea8be0e9e2b4a9deff3daacefd9de307f2a601b2c3cc6c9ade37b710f5d2 +size 15892204000 diff --git a/arctune-gpt20b.i1-Q6_K.gguf b/arctune-gpt20b.i1-Q6_K.gguf new file mode 100644 index 0000000..a5e6fe9 --- /dev/null +++ b/arctune-gpt20b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cabed5e36b849be036aba8c8f0be03cea243937f9545ce9f8dc1487b953dc5d +size 22193344480 diff --git a/arctune-gpt20b.imatrix.gguf b/arctune-gpt20b.imatrix.gguf new file mode 100644 index 0000000..304e9d8 --- /dev/null +++ b/arctune-gpt20b.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba89e220f24dbc6e312ee9a63b07e95ec65a7bcafdaa6d2ce622e900cf2fca28 +size 28079776