commit dc2e80c4484a5832adf13bbcb18642c769f855e2 Author: ModelHub XC Date: Mon Jun 15 09:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-ko-7b-instruct-v0.50-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d26d427 --- /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-v0.50.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-ko-7b-instruct-v0.50.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f78a33f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: lemon-mint/gemma-ko-7b-instruct-v0.50 +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: +- korean +- gemma +- pytorch +--- +## About + + + + + + +static quants of https://huggingface.co/lemon-mint/gemma-ko-7b-instruct-v0.50 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-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-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-ko-7b-instruct-v0.50-GGUF/resolve/main/gemma-ko-7b-instruct-v0.50.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. + + diff --git a/gemma-ko-7b-instruct-v0.50.IQ4_XS.gguf b/gemma-ko-7b-instruct-v0.50.IQ4_XS.gguf new file mode 100644 index 0000000..dd9b274 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814251d5a6c0c656bacc3e1d29cca402a64e19b7790ce978936a8081f844faf3 +size 4805013920 diff --git a/gemma-ko-7b-instruct-v0.50.Q2_K.gguf b/gemma-ko-7b-instruct-v0.50.Q2_K.gguf new file mode 100644 index 0000000..d2ef6a7 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43448763810aeabd278b9fcd5f2191117165c23b9560e11ab101ce2a02301d2 +size 3481448864 diff --git a/gemma-ko-7b-instruct-v0.50.Q3_K_L.gguf b/gemma-ko-7b-instruct-v0.50.Q3_K_L.gguf new file mode 100644 index 0000000..467778e --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc086b7e0e79c6c3b261aae8c576cb54b3ced38a94c9f63227ddc29f4f38830 +size 4709069216 diff --git a/gemma-ko-7b-instruct-v0.50.Q3_K_M.gguf b/gemma-ko-7b-instruct-v0.50.Q3_K_M.gguf new file mode 100644 index 0000000..4ed31a4 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37e17180ef2df785730b08d19880196621985e0c8f502bfb170fb5102ad53411 +size 4369330592 diff --git a/gemma-ko-7b-instruct-v0.50.Q3_K_S.gguf b/gemma-ko-7b-instruct-v0.50.Q3_K_S.gguf new file mode 100644 index 0000000..6967bca --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5990fe71fc8a0c4181c5ed94eea036358b514f2be47d8f0fa3762618b5947474 +size 3982406048 diff --git a/gemma-ko-7b-instruct-v0.50.Q4_K_M.gguf b/gemma-ko-7b-instruct-v0.50.Q4_K_M.gguf new file mode 100644 index 0000000..116003c --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c991c08c22664138ed77490b29afe4235142334f02a1d7e4404482c48cd8d9e7 +size 5329760672 diff --git a/gemma-ko-7b-instruct-v0.50.Q4_K_S.gguf b/gemma-ko-7b-instruct-v0.50.Q4_K_S.gguf new file mode 100644 index 0000000..fd12c0d --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:295ec4f0107ce14b5efe3153bac1a125d2f6c45e6b3d624f9732b43e94e3f303 +size 5046448544 diff --git a/gemma-ko-7b-instruct-v0.50.Q5_K_M.gguf b/gemma-ko-7b-instruct-v0.50.Q5_K_M.gguf new file mode 100644 index 0000000..95a2374 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716ae82e96afd372b8be76bd6622c4107364a9aa5ae7d76b15d74cf7103d7f89 +size 6144504224 diff --git a/gemma-ko-7b-instruct-v0.50.Q5_K_S.gguf b/gemma-ko-7b-instruct-v0.50.Q5_K_S.gguf new file mode 100644 index 0000000..35077dd --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67a5d2c601142cd6cbbcace105b28ef9b4c87190cac007d4d99fb461da14e85e +size 5980729760 diff --git a/gemma-ko-7b-instruct-v0.50.Q6_K.gguf b/gemma-ko-7b-instruct-v0.50.Q6_K.gguf new file mode 100644 index 0000000..10a5fae --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8337bd4207994c11d7fea7b9e6b0f50949b7fd86efeec60f166d6d5c6097624f +size 7010169248 diff --git a/gemma-ko-7b-instruct-v0.50.Q8_0.gguf b/gemma-ko-7b-instruct-v0.50.Q8_0.gguf new file mode 100644 index 0000000..f669e83 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2d486145c32e6526beeab6506290251ff326e8963bb900645e22a72d8fe0a0 +size 9077846432 diff --git a/gemma-ko-7b-instruct-v0.50.f16.gguf b/gemma-ko-7b-instruct-v0.50.f16.gguf new file mode 100644 index 0000000..cff91f0 --- /dev/null +++ b/gemma-ko-7b-instruct-v0.50.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f2a85e3db44d58ce62fceb85eca86471e9e1a0f6798ad24c72a0b06342d48c +size 17081758112