commit f17aab55e57d2af3dfca78606db4fc1b26a8a2d0 Author: ModelHub XC Date: Tue Jun 16 19:40:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GeumokGPT-Lite-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e795ec2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +GeumokGPT-Lite.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GeumokGPT-Lite.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GeumokGPT-Lite.IQ4_XS.gguf b/GeumokGPT-Lite.IQ4_XS.gguf new file mode 100644 index 0000000..77151a1 --- /dev/null +++ b/GeumokGPT-Lite.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6639a2bd3b7a96e446a57ae983fc0f32374959818724947d3d0000dac73f5c16 +size 718167744 diff --git a/GeumokGPT-Lite.Q2_K.gguf b/GeumokGPT-Lite.Q2_K.gguf new file mode 100644 index 0000000..906e95a --- /dev/null +++ b/GeumokGPT-Lite.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1585ce779b8027c8754a2a541985aa029607173d1f228c1323bb2667b0d65aba +size 689814720 diff --git a/GeumokGPT-Lite.Q3_K_L.gguf b/GeumokGPT-Lite.Q3_K_L.gguf new file mode 100644 index 0000000..f999ae1 --- /dev/null +++ b/GeumokGPT-Lite.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7b31c27a8443ebbdf90e08e812ece6e3f3a48e608fe6d38daf874e6d535359 +size 751575744 diff --git a/GeumokGPT-Lite.Q3_K_M.gguf b/GeumokGPT-Lite.Q3_K_M.gguf new file mode 100644 index 0000000..c27b589 --- /dev/null +++ b/GeumokGPT-Lite.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ae2d98ff4efaa55c80333113d95faedbbd99f887546c1c3ef68b3b9df6e3785 +size 722416320 diff --git a/GeumokGPT-Lite.Q3_K_S.gguf b/GeumokGPT-Lite.Q3_K_S.gguf new file mode 100644 index 0000000..33b2b26 --- /dev/null +++ b/GeumokGPT-Lite.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb03223e64a74df50612395ca15a2ba75cfb250b0cb8c7a8b89349802674dd3 +size 688856256 diff --git a/GeumokGPT-Lite.Q4_K_M.gguf b/GeumokGPT-Lite.Q4_K_M.gguf new file mode 100644 index 0000000..69da0dd --- /dev/null +++ b/GeumokGPT-Lite.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a71fae1fefb19d693884053f3d5009cfdbed7886c4ce844f9b9773493bf8f9e +size 806058432 diff --git a/GeumokGPT-Lite.Q4_K_S.gguf b/GeumokGPT-Lite.Q4_K_S.gguf new file mode 100644 index 0000000..f2bcc0f --- /dev/null +++ b/GeumokGPT-Lite.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:027c49fd0997b06afd244629f344d6721f9b6a1a324f3e2885eddd0d8e33e2e7 +size 780993216 diff --git a/GeumokGPT-Lite.Q5_K_M.gguf b/GeumokGPT-Lite.Q5_K_M.gguf new file mode 100644 index 0000000..6ed3034 --- /dev/null +++ b/GeumokGPT-Lite.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7002497bc956beb5ff9f81489986f22594490ff1eaea3a1938e14bc28c78ceb +size 851345856 diff --git a/GeumokGPT-Lite.Q5_K_S.gguf b/GeumokGPT-Lite.Q5_K_S.gguf new file mode 100644 index 0000000..45cc230 --- /dev/null +++ b/GeumokGPT-Lite.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c03d040484eda822cad003f2993ee8f3ac15e33161e7b79f0f02be496b3f5c +size 836399808 diff --git a/GeumokGPT-Lite.Q6_K.gguf b/GeumokGPT-Lite.Q6_K.gguf new file mode 100644 index 0000000..78d9b41 --- /dev/null +++ b/GeumokGPT-Lite.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f99883d3d7ec8a4624499fda36098430c50378fb08e5c2f4a6595df94c5f2fa +size 1011738816 diff --git a/GeumokGPT-Lite.Q8_0.gguf b/GeumokGPT-Lite.Q8_0.gguf new file mode 100644 index 0000000..e1af004 --- /dev/null +++ b/GeumokGPT-Lite.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10891023a1195e4bd2eab92e0ffbea2e60a90c503f05e0d5e18010812a51c994 +size 1069306560 diff --git a/GeumokGPT-Lite.f16.gguf b/GeumokGPT-Lite.f16.gguf new file mode 100644 index 0000000..6a85971 --- /dev/null +++ b/GeumokGPT-Lite.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee75879137ffd2308e283c617a748527f84cf71aaae3d2ab034613e7a58fcc29 +size 2006573760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c82e89f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Geumokmiddleschool/GeumokGPT-Lite +language: +- ko +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + +static quants of https://huggingface.co/Geumokmiddleschool/GeumokGPT-Lite + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GeumokGPT-Lite-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.Q8_0.gguf) | Q8_0 | 1.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GeumokGPT-Lite-GGUF/resolve/main/GeumokGPT-Lite.f16.gguf) | f16 | 2.1 | 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. + +