commit 2235bbc93e1faeacdd37f66f496657a600f34d4c Author: ModelHub XC Date: Wed Jun 24 21:34:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..980b9ee --- /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-7b-sft-dpo-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +ko-gemma-7b-sft-dpo-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9918429 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ihopper/ko-gemma-7b-sft-dpo-v1.0 +language: +- ko +- en +library_name: transformers +license: other +license_link: https://ai.google.dev/gemma/terms +license_name: gemma-terms-of-use +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- korean +- gemma +- pytorch +--- +## About + + + + + + +static quants of https://huggingface.co/ihopper/ko-gemma-7b-sft-dpo-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#ko-gemma-7b-sft-dpo-v1.0-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-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-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q2_K.gguf) | Q2_K | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q3_K_S.gguf) | Q3_K_S | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q3_K_M.gguf) | Q3_K_M | 4.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q3_K_L.gguf) | Q3_K_L | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.IQ4_XS.gguf) | IQ4_XS | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q4_K_S.gguf) | Q4_K_S | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q4_K_M.gguf) | Q4_K_M | 5.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q5_K_S.gguf) | Q5_K_S | 6.1 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q5_K_M.gguf) | Q5_K_M | 6.2 | | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q6_K.gguf) | Q6_K | 7.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.Q8_0.gguf) | Q8_0 | 9.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/ko-gemma-7b-sft-dpo-v1.0-GGUF/resolve/main/ko-gemma-7b-sft-dpo-v1.0.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/ko-gemma-7b-sft-dpo-v1.0.IQ4_XS.gguf b/ko-gemma-7b-sft-dpo-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..5495852 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a50a7a8a59066887f3d22fef18e1620e1a1beb842b9bb3d3514e393271e34c7a +size 4805013824 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q2_K.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q2_K.gguf new file mode 100644 index 0000000..6a44d7e --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae048b5eeddddad607e988290f5e7bc7101fd74c11fd965512f02243242395c1 +size 3481448768 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q3_K_L.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..00b924c --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2db57baa9d59e430ee13982e303dac1f65179e80b2a69cfcb93fafa0a96c57de +size 4709069120 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q3_K_M.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..8ba0125 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4408ed62010a44ae56dfb392d3a0e06957613f032d66241ff09c70cd8c729dbf +size 4369330496 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q3_K_S.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..aea241b --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:852b57392242a794654faddfda10eb0805b4380d7342ce47649faf6718be9d7f +size 3982405952 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q4_K_M.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..d37af88 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bc8284bbc0b6779528a198b31f0430b7b9533dda7f85fc9271e3882dbff9e32 +size 5329760576 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q4_K_S.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..1d5d9bd --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74cdded3f028b8acd948ac108323b20d0af85c6113f086c795d9fd4ec5cd8316 +size 5046448448 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q5_K_M.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..415491e --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4351fd3000d1b3be92d25ccdbfad105b52bc7f29918145e50ceebbb4502bb4ef +size 6144504128 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q5_K_S.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..d7b2088 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2606edd0f7b2bd923f85a98365791a8ac70caf94c6abda5d4ad15fe931339c07 +size 5980729664 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q6_K.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q6_K.gguf new file mode 100644 index 0000000..9f06855 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7a34afc9be580fcbcc5c877a78ff27c67e89f1ebb8dbeccde6c4b7ece906e3 +size 7010169152 diff --git a/ko-gemma-7b-sft-dpo-v1.0.Q8_0.gguf b/ko-gemma-7b-sft-dpo-v1.0.Q8_0.gguf new file mode 100644 index 0000000..f9608b7 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15fd6062b18923f9b4c454112e37afadb9ce77c1444fb694b9ece17f1b5ad93 +size 9077846336 diff --git a/ko-gemma-7b-sft-dpo-v1.0.f16.gguf b/ko-gemma-7b-sft-dpo-v1.0.f16.gguf new file mode 100644 index 0000000..d46bed6 --- /dev/null +++ b/ko-gemma-7b-sft-dpo-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec0567fbe7f1b581c491bcf7b4d7cb0ba57c31974698c61df9937c7050c8d5ec +size 17081758016