commit c99309d446d1a34d34c894f9eecebd0634f9aff8 Author: ModelHub XC Date: Wed Jun 17 14:02:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-ko-7b-instruct-v0.71-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c355b0 --- /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-7b-instruct-v0.71.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.71.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9be5c60 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: lemon-mint/gemma-ko-7b-instruct-v0.71 +language: +- ko +- en +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- korean +- gemma +- pytorch +--- +## About + + + + + + +static quants of https://huggingface.co/lemon-mint/gemma-ko-7b-instruct-v0.71 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-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-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.71-GGUF/resolve/main/gemma-ko-7b-instruct-v0.71.f16.gguf) | f16 | 17.2 | 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. 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/gemma-ko-7b-instruct-v0.71.IQ4_XS.gguf b/gemma-ko-7b-instruct-v0.71.IQ4_XS.gguf new file mode 100644 index 0000000..07a05de --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a2d732e5d54bbdfcbf9e73efc48ac159967d1fa623e2443096e1e2f05c74f1 +size 4805012768 diff --git a/gemma-ko-7b-instruct-v0.71.Q2_K.gguf b/gemma-ko-7b-instruct-v0.71.Q2_K.gguf new file mode 100644 index 0000000..d5fbaa3 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68dc3938e045ed0da6c01b72544b8dbb67476f008f08d31a58651e3982e4b4a1 +size 3481447712 diff --git a/gemma-ko-7b-instruct-v0.71.Q3_K_L.gguf b/gemma-ko-7b-instruct-v0.71.Q3_K_L.gguf new file mode 100644 index 0000000..a45358b --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6912da2c7b56f7d77dd5796f64a564fcea4dd6e4d5ca8d5779d8d7d24e42e529 +size 4709068064 diff --git a/gemma-ko-7b-instruct-v0.71.Q3_K_M.gguf b/gemma-ko-7b-instruct-v0.71.Q3_K_M.gguf new file mode 100644 index 0000000..d21aeaa --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42ba26383beb38fd2885ae56631352c1bae234e481e455b72f1572d18106aea3 +size 4369329440 diff --git a/gemma-ko-7b-instruct-v0.71.Q3_K_S.gguf b/gemma-ko-7b-instruct-v0.71.Q3_K_S.gguf new file mode 100644 index 0000000..88896a0 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89dea8aeb778032750649c993f907acc98b14cc7951efc64ee88e1a775a5fe0 +size 3982404896 diff --git a/gemma-ko-7b-instruct-v0.71.Q4_K_M.gguf b/gemma-ko-7b-instruct-v0.71.Q4_K_M.gguf new file mode 100644 index 0000000..f4a8bb8 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a094cdf80455e44bafed263839765fdc8319bca4b813f3939773efde2b99dd9 +size 5329759520 diff --git a/gemma-ko-7b-instruct-v0.71.Q4_K_S.gguf b/gemma-ko-7b-instruct-v0.71.Q4_K_S.gguf new file mode 100644 index 0000000..1aaf57b --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba722ddb2cada26066bca0b0204d8fcdfffbc065b614df6192cdba8ac0385629 +size 5046447392 diff --git a/gemma-ko-7b-instruct-v0.71.Q5_K_M.gguf b/gemma-ko-7b-instruct-v0.71.Q5_K_M.gguf new file mode 100644 index 0000000..e059e16 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36d41565e4024f8109e54a69dd2262c004d6b83e8b342fe8eced78000e2847d +size 6144503072 diff --git a/gemma-ko-7b-instruct-v0.71.Q5_K_S.gguf b/gemma-ko-7b-instruct-v0.71.Q5_K_S.gguf new file mode 100644 index 0000000..e6a07b0 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:101c7209785538372f7cff5961231cbdeb97025326049fa59ee88e28556c3b43 +size 5980728608 diff --git a/gemma-ko-7b-instruct-v0.71.Q6_K.gguf b/gemma-ko-7b-instruct-v0.71.Q6_K.gguf new file mode 100644 index 0000000..664c5e2 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1e80eae4e97ff9ebb296cb926be56661da1e2c2cbb01a915234a1091198211 +size 7010168096 diff --git a/gemma-ko-7b-instruct-v0.71.Q8_0.gguf b/gemma-ko-7b-instruct-v0.71.Q8_0.gguf new file mode 100644 index 0000000..e623e99 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694c09937f32a38df9c3c686de71127d70da7bc9bebc00d70ef1af334ca60b80 +size 9077845280 diff --git a/gemma-ko-7b-instruct-v0.71.f16.gguf b/gemma-ko-7b-instruct-v0.71.f16.gguf new file mode 100644 index 0000000..365449c --- /dev/null +++ b/gemma-ko-7b-instruct-v0.71.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a91149bfcbd17cfe77734ed1c2009a8c0f2492104a54198344f694313d9f3a7 +size 17081756960