commit 73e76ec40844596a9b783426770f39933b500c23 Author: ModelHub XC Date: Wed Jun 17 19:53:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ko-gemma-2-9b-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2f9064f --- /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 +ko-gemma-2-9b-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-2-9b-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9294b9f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: rtzr/ko-gemma-2-9b-it +extra_gated_button_content: Acknowledge license +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +language: +- ko +library_name: transformers +license: gemma +quantized_by: mradermacher +tags: +- conversational +--- +## About + + + + + + +static quants of https://huggingface.co/rtzr/ko-gemma-2-9b-it + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ko-gemma-2-9b-it-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/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-2-9b-it-GGUF/resolve/main/ko-gemma-2-9b-it.f16.gguf) | f16 | 18.6 | 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/ko-gemma-2-9b-it.IQ4_XS.gguf b/ko-gemma-2-9b-it.IQ4_XS.gguf new file mode 100644 index 0000000..bf6329a --- /dev/null +++ b/ko-gemma-2-9b-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60453ddbd68150de5df38d61d2d31e75edb1b918d1656069c97eaa561c5df735 +size 5223171616 diff --git a/ko-gemma-2-9b-it.Q2_K.gguf b/ko-gemma-2-9b-it.Q2_K.gguf new file mode 100644 index 0000000..181ddc6 --- /dev/null +++ b/ko-gemma-2-9b-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1764b431a2c7f460389c176c8af78bfeea683440cfb8d638750abce84ca0dbfb +size 3805398560 diff --git a/ko-gemma-2-9b-it.Q3_K_L.gguf b/ko-gemma-2-9b-it.Q3_K_L.gguf new file mode 100644 index 0000000..23b25ef --- /dev/null +++ b/ko-gemma-2-9b-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef1f91bdb1a4a3f74ee09b74b6441bd7bd68f75f03ebca62b8b450c77b3c184c +size 5132453408 diff --git a/ko-gemma-2-9b-it.Q3_K_M.gguf b/ko-gemma-2-9b-it.Q3_K_M.gguf new file mode 100644 index 0000000..4591cc7 --- /dev/null +++ b/ko-gemma-2-9b-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e802fd57a7876e8e171c0c1e2604e2d72b03550cf5af32115e79fffff198f49 +size 4761781792 diff --git a/ko-gemma-2-9b-it.Q3_K_S.gguf b/ko-gemma-2-9b-it.Q3_K_S.gguf new file mode 100644 index 0000000..b351e80 --- /dev/null +++ b/ko-gemma-2-9b-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74278c493982d555b7e24f3b7e02530e77bf9be4c684a28026f213bf4ad0113b +size 4337665568 diff --git a/ko-gemma-2-9b-it.Q4_K_M.gguf b/ko-gemma-2-9b-it.Q4_K_M.gguf new file mode 100644 index 0000000..6fe8bc7 --- /dev/null +++ b/ko-gemma-2-9b-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63905f53dc51fb1218152eec9d1e64a31313892d51483afb39c82e787623dba8 +size 5761058336 diff --git a/ko-gemma-2-9b-it.Q4_K_S.gguf b/ko-gemma-2-9b-it.Q4_K_S.gguf new file mode 100644 index 0000000..243c9df --- /dev/null +++ b/ko-gemma-2-9b-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c34e4f79e8f2a4e9b5b072f8c95dc3afeaa0f36a2af4f90bc9005ed34b74def7 +size 5478925856 diff --git a/ko-gemma-2-9b-it.Q5_K_M.gguf b/ko-gemma-2-9b-it.Q5_K_M.gguf new file mode 100644 index 0000000..201f25f --- /dev/null +++ b/ko-gemma-2-9b-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2dcb5477a2b24a921ad7f9304de7da11e048949ba0db6ac0ff4750eeefbd92a +size 6647367200 diff --git a/ko-gemma-2-9b-it.Q5_K_S.gguf b/ko-gemma-2-9b-it.Q5_K_S.gguf new file mode 100644 index 0000000..0aefb63 --- /dev/null +++ b/ko-gemma-2-9b-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c7147282bf13fc23656f769dbf86a09d2ffb24be335157d45d5f6c8a9a53f0 +size 6483592736 diff --git a/ko-gemma-2-9b-it.Q6_K.gguf b/ko-gemma-2-9b-it.Q6_K.gguf new file mode 100644 index 0000000..432e4aa --- /dev/null +++ b/ko-gemma-2-9b-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a03a74d57367399b70ee4c766a0c3f59454620bbfee328534624dee257cf6e2 +size 7589070368 diff --git a/ko-gemma-2-9b-it.Q8_0.gguf b/ko-gemma-2-9b-it.Q8_0.gguf new file mode 100644 index 0000000..203954e --- /dev/null +++ b/ko-gemma-2-9b-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102ebfa8b632248287e6a806274409db8fbc1d8222a0d9283b0ea7abb2895219 +size 9827149344 diff --git a/ko-gemma-2-9b-it.f16.gguf b/ko-gemma-2-9b-it.f16.gguf new file mode 100644 index 0000000..cb6a228 --- /dev/null +++ b/ko-gemma-2-9b-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0bc49c2a635e1ad8bf531f6fce7c6bb2bfdb99abb778acce0794e4d33ae16c9 +size 18490680864