commit d4e03a109d995a0f518375305d4b0f4daaf25901 Author: ModelHub XC Date: Fri Jun 26 02:16:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-ko-2b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..24b568e --- /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 +gemma-ko-2b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-2b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1bf2229 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: beomi/gemma-ko-2b +language: +- ko +- en +library_name: transformers +license: other +license_link: https://ai.google.dev/gemma/terms +license_name: gemma-terms-of-use +quantized_by: mradermacher +tags: +- pytorch +--- +## About + + + + + + +static quants of https://huggingface.co/beomi/gemma-ko-2b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-ko-2b-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/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q2_K.gguf) | Q2_K | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q3_K_L.gguf) | Q3_K_L | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q4_K_M.gguf) | Q4_K_M | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q5_K_S.gguf) | Q5_K_S | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q5_K_M.gguf) | Q5_K_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q6_K.gguf) | Q6_K | 2.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-2b-GGUF/resolve/main/gemma-ko-2b.f16.gguf) | f16 | 5.1 | 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. + + diff --git a/gemma-ko-2b.IQ4_XS.gguf b/gemma-ko-2b.IQ4_XS.gguf new file mode 100644 index 0000000..bd34e3d --- /dev/null +++ b/gemma-ko-2b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e622482f5a1b2d9c00eefc67d7ed2536466d479aac4bcbbfd04f15f1486e6475 +size 1501218976 diff --git a/gemma-ko-2b.Q2_K.gguf b/gemma-ko-2b.Q2_K.gguf new file mode 100644 index 0000000..1d05ece --- /dev/null +++ b/gemma-ko-2b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca694d14bee235c874b243d3c122125fb20cb4a26a134af4a869882f436f0abf +size 1157925024 diff --git a/gemma-ko-2b.Q3_K_L.gguf b/gemma-ko-2b.Q3_K_L.gguf new file mode 100644 index 0000000..23c0855 --- /dev/null +++ b/gemma-ko-2b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0d8428299990be71deebdb4edb88a97656ff4764c7eb38307e9295210e6866a +size 1465591968 diff --git a/gemma-ko-2b.Q3_K_M.gguf b/gemma-ko-2b.Q3_K_M.gguf new file mode 100644 index 0000000..175bac4 --- /dev/null +++ b/gemma-ko-2b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74d933f40128e13f48e46eac500161836b2251dfa2253f6d629b45fb14750273 +size 1383803040 diff --git a/gemma-ko-2b.Q3_K_S.gguf b/gemma-ko-2b.Q3_K_S.gguf new file mode 100644 index 0000000..1780698 --- /dev/null +++ b/gemma-ko-2b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48309d6cb15893e7ed690facdedfe7fa796b7a8615b5ed5890b2fbbe07470e69 +size 1287981216 diff --git a/gemma-ko-2b.Q4_K_M.gguf b/gemma-ko-2b.Q4_K_M.gguf new file mode 100644 index 0000000..bc755c7 --- /dev/null +++ b/gemma-ko-2b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1256afe2f9ee6a5d3a55a1d26639c49dd8770b472365c36fa4f9ef9c5f00d107 +size 1630263456 diff --git a/gemma-ko-2b.Q4_K_S.gguf b/gemma-ko-2b.Q4_K_S.gguf new file mode 100644 index 0000000..441a218 --- /dev/null +++ b/gemma-ko-2b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6e899b80b59fc4179070e7e9569c323e6ee3b926caf51cd069d5fd7a5f7d0a +size 1559840928 diff --git a/gemma-ko-2b.Q5_K_M.gguf b/gemma-ko-2b.Q5_K_M.gguf new file mode 100644 index 0000000..e7030d2 --- /dev/null +++ b/gemma-ko-2b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06d54496393747fd20a4fca48efc2c9daa0c42d7c8135da36d6c4232ef5eb87f +size 1839650976 diff --git a/gemma-ko-2b.Q5_K_S.gguf b/gemma-ko-2b.Q5_K_S.gguf new file mode 100644 index 0000000..b3d53e7 --- /dev/null +++ b/gemma-ko-2b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d257a8067ec0ad738fa7b28608c007fb08f46d3ea2868b758ae7649f2b0cd7 +size 1798916256 diff --git a/gemma-ko-2b.Q6_K.gguf b/gemma-ko-2b.Q6_K.gguf new file mode 100644 index 0000000..3f5e645 --- /dev/null +++ b/gemma-ko-2b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc603985bec97e52fd5087f3e6c713d7bbecaa0e43d50561f44e6f82ec4f5831 +size 2062125216 diff --git a/gemma-ko-2b.Q8_0.gguf b/gemma-ko-2b.Q8_0.gguf new file mode 100644 index 0000000..16e1d39 --- /dev/null +++ b/gemma-ko-2b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a0011a81d185e48db28eb4fd1dff6ff39d29e90ad92de3ce3f5242afe4d554 +size 2669070496 diff --git a/gemma-ko-2b.f16.gguf b/gemma-ko-2b.f16.gguf new file mode 100644 index 0000000..07567ca --- /dev/null +++ b/gemma-ko-2b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11a38a0c76bacb6ea692725e7a1bf58fadbd4e32053c70cb2dcb1400fbcccf05 +size 5018536096