commit 6be82aecd67333a6f222601cc93a8bbe65f7e55d Author: ModelHub XC Date: Thu Jun 11 17:38:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/YugoGPT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c69437f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +YugoGPT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +YugoGPT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..36b4b56 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: gordicaleksa/YugoGPT +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/gordicaleksa/YugoGPT + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/YugoGPT-i1-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/YugoGPT-GGUF/resolve/main/YugoGPT.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/YugoGPT-GGUF/resolve/main/YugoGPT.f16.gguf) | f16 | 14.6 | 16 bpw, overkill | + +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. + + diff --git a/YugoGPT.IQ4_XS.gguf b/YugoGPT.IQ4_XS.gguf new file mode 100644 index 0000000..e1ad5fc --- /dev/null +++ b/YugoGPT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37720675189521c3187473e9812f7b14392277415e8b2e4a4ffad984d6905ca4 +size 3944389024 diff --git a/YugoGPT.Q2_K.gguf b/YugoGPT.Q2_K.gguf new file mode 100644 index 0000000..f1455fb --- /dev/null +++ b/YugoGPT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1375b4231cfcc39379910de7a846dadef81f61666da7481daad140303a48d3 +size 2719242656 diff --git a/YugoGPT.Q3_K_L.gguf b/YugoGPT.Q3_K_L.gguf new file mode 100644 index 0000000..3ac4425 --- /dev/null +++ b/YugoGPT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ea1017507687038bed7613b41a1d77d6c4c24d0020ae4bb226749f3e32d39e6 +size 3822025120 diff --git a/YugoGPT.Q3_K_M.gguf b/YugoGPT.Q3_K_M.gguf new file mode 100644 index 0000000..c4bcd30 --- /dev/null +++ b/YugoGPT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:862efc265224a52e9c7878bad732d592814d14d03b3612f71d108ef42d0c7a9c +size 3518986656 diff --git a/YugoGPT.Q3_K_S.gguf b/YugoGPT.Q3_K_S.gguf new file mode 100644 index 0000000..d44e544 --- /dev/null +++ b/YugoGPT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61ebbfb382eeda32a62ebb2bbab9d78d5aab32d99e97a1d7eb7b59655d45c856 +size 3164567968 diff --git a/YugoGPT.Q4_0_4_4.gguf b/YugoGPT.Q4_0_4_4.gguf new file mode 100644 index 0000000..b30789d --- /dev/null +++ b/YugoGPT.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7721d2c087fffdd08569148c52ecb5b2bae2ab394a747e06d13cf16c205b854b +size 4108917152 diff --git a/YugoGPT.Q4_K_M.gguf b/YugoGPT.Q4_K_M.gguf new file mode 100644 index 0000000..c8a5e2e --- /dev/null +++ b/YugoGPT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987e1dbe1887aa464165cad94ce86d9fe5a69cd06647e2e213cdec0abd8cd4dc +size 4368439712 diff --git a/YugoGPT.Q4_K_S.gguf b/YugoGPT.Q4_K_S.gguf new file mode 100644 index 0000000..aabab59 --- /dev/null +++ b/YugoGPT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef283e5cf8849abb399125682650e6df33d911ebbc6ae3ddc860b50b9cd2658 +size 4140374432 diff --git a/YugoGPT.Q5_K_M.gguf b/YugoGPT.Q5_K_M.gguf new file mode 100644 index 0000000..a71bf29 --- /dev/null +++ b/YugoGPT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316b72cb0b75f76da1b0aca0e66becccc50a3b3b49511199f5fcb02c533ee600 +size 5131409824 diff --git a/YugoGPT.Q5_K_S.gguf b/YugoGPT.Q5_K_S.gguf new file mode 100644 index 0000000..88730f2 --- /dev/null +++ b/YugoGPT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c763282df294070d875e301b3b922b5f00ec5849fadf8b0e9e014761de7116 +size 4997716384 diff --git a/YugoGPT.Q6_K.gguf b/YugoGPT.Q6_K.gguf new file mode 100644 index 0000000..7c0773d --- /dev/null +++ b/YugoGPT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6cc424486daefd701219345b612f09a5a1624238ee088d195dfa744205b9917 +size 5942065568 diff --git a/YugoGPT.Q8_0.gguf b/YugoGPT.Q8_0.gguf new file mode 100644 index 0000000..50144cd --- /dev/null +++ b/YugoGPT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9b16a54b7e4c11f5efe77136a2878906bdbb2cebb79d262f6bb2ab6cd4fce7 +size 7695858080 diff --git a/YugoGPT.f16.gguf b/YugoGPT.f16.gguf new file mode 100644 index 0000000..2b9274d --- /dev/null +++ b/YugoGPT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8bcdf1e3d8a293fdd1690ba4e50a85728922aa8a21c137932f4642d5b2dac3 +size 14484732320