commit a556466197b0d5dd98faefa6e9454f8acdc32f87 Author: ModelHub XC Date: Fri Jun 26 23:06:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ko-Luxia-8B-it-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..79e49c9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-Luxia-8B-it.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.f16.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Luxia-8B-it.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ko-Luxia-8B-it.IQ3_M.gguf b/Ko-Luxia-8B-it.IQ3_M.gguf new file mode 100644 index 0000000..0a87293 --- /dev/null +++ b/Ko-Luxia-8B-it.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29bdb9bce66b2f0500741e8b95627db42968eb6bcdd191231aa876cab3fcb9ff +size 3875509632 diff --git a/Ko-Luxia-8B-it.IQ3_S.gguf b/Ko-Luxia-8B-it.IQ3_S.gguf new file mode 100644 index 0000000..5bb749e --- /dev/null +++ b/Ko-Luxia-8B-it.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba198e355760e99e9cfae9440916bcc1091cc8f248a8dbb6495dfa8f7956811 +size 3773011328 diff --git a/Ko-Luxia-8B-it.IQ3_XS.gguf b/Ko-Luxia-8B-it.IQ3_XS.gguf new file mode 100644 index 0000000..af23973 --- /dev/null +++ b/Ko-Luxia-8B-it.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6c2ed4e8fc224c3e07d397a9da73d874cbdb4b07082324686e81801c6f9b93 +size 3609433472 diff --git a/Ko-Luxia-8B-it.IQ4_XS.gguf b/Ko-Luxia-8B-it.IQ4_XS.gguf new file mode 100644 index 0000000..e2dd9cf --- /dev/null +++ b/Ko-Luxia-8B-it.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d4eb5167f94433d0bb361c39077bf3e4787238acc7d466f249e924743afb09a +size 4582344064 diff --git a/Ko-Luxia-8B-it.Q2_K.gguf b/Ko-Luxia-8B-it.Q2_K.gguf new file mode 100644 index 0000000..e9c4d56 --- /dev/null +++ b/Ko-Luxia-8B-it.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6f743b54081ccfbbac8006e32fc054a9fb694bd48b3a0602f28d0022d20c3b9 +size 3262522752 diff --git a/Ko-Luxia-8B-it.Q3_K_L.gguf b/Ko-Luxia-8B-it.Q3_K_L.gguf new file mode 100644 index 0000000..3cee254 --- /dev/null +++ b/Ko-Luxia-8B-it.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92cbc6248ee48f29303314e0a5148a3a2d0a51fe84bd6396de0dc51a1292565c +size 4412642688 diff --git a/Ko-Luxia-8B-it.Q3_K_M.gguf b/Ko-Luxia-8B-it.Q3_K_M.gguf new file mode 100644 index 0000000..4a90ed4 --- /dev/null +++ b/Ko-Luxia-8B-it.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9221e0ec36d9272c06dadebddf645c56b82739c877ad5a1e0fd8235db2099dd7 +size 4109604224 diff --git a/Ko-Luxia-8B-it.Q3_K_S.gguf b/Ko-Luxia-8B-it.Q3_K_S.gguf new file mode 100644 index 0000000..809ca11 --- /dev/null +++ b/Ko-Luxia-8B-it.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:003665edd5e8298e93909b6c6115146cb5d99f3b5db0bfa4a79b92b7913d2169 +size 3755185536 diff --git a/Ko-Luxia-8B-it.Q4_K_M.gguf b/Ko-Luxia-8B-it.Q4_K_M.gguf new file mode 100644 index 0000000..055b355 --- /dev/null +++ b/Ko-Luxia-8B-it.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f935c765b72983d445357589af7693a25c5dc34d1cad6398cc665318293fb25 +size 5020960128 diff --git a/Ko-Luxia-8B-it.Q4_K_S.gguf b/Ko-Luxia-8B-it.Q4_K_S.gguf new file mode 100644 index 0000000..e6cc0d5 --- /dev/null +++ b/Ko-Luxia-8B-it.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f198accc96ef63af1d3754953c680a969e2d77f40d66b2f7c35ff0e2379acf0 +size 4792894848 diff --git a/Ko-Luxia-8B-it.Q5_K_M.gguf b/Ko-Luxia-8B-it.Q5_K_M.gguf new file mode 100644 index 0000000..09e4b5f --- /dev/null +++ b/Ko-Luxia-8B-it.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:282212875950b7d1a51a5cd8263ad65188ba27371990d5737c69d6bd13da4f1c +size 5842191744 diff --git a/Ko-Luxia-8B-it.Q5_K_S.gguf b/Ko-Luxia-8B-it.Q5_K_S.gguf new file mode 100644 index 0000000..989e2fa --- /dev/null +++ b/Ko-Luxia-8B-it.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b49e0e587571a5228bbb6d97875ceec3985e8cbafe098a8649fa55ae814be5 +size 5708498304 diff --git a/Ko-Luxia-8B-it.Q6_K.gguf b/Ko-Luxia-8B-it.Q6_K.gguf new file mode 100644 index 0000000..e51709d --- /dev/null +++ b/Ko-Luxia-8B-it.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3f6d89672c0afb38d37140d89c09c3872aeba2f3afb78558d20091d65498a37 +size 6714750336 diff --git a/Ko-Luxia-8B-it.Q8_0.gguf b/Ko-Luxia-8B-it.Q8_0.gguf new file mode 100644 index 0000000..b77e5cf --- /dev/null +++ b/Ko-Luxia-8B-it.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8719c89753ef621d2c0278a96ce29035a35d2f273236dd22aafd6903c06c5d31 +size 8694306176 diff --git a/Ko-Luxia-8B-it.f16.gguf b/Ko-Luxia-8B-it.f16.gguf new file mode 100644 index 0000000..53a61d5 --- /dev/null +++ b/Ko-Luxia-8B-it.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3de6c964725db2094164d954f69c5e935bdf89d4d82f076979548422827dca4d +size 16357102976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2d17873 --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: MDDDDR/Ko-Luxia-8B-it-v0.1 +datasets: +- kyujinpy/KOpen-platypus +language: +- ko +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/MDDDDR/Ko-Luxia-8B-it-v0.1 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.IQ3_XS.gguf) | IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.IQ3_S.gguf) | IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.IQ3_M.gguf) | IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Luxia-8B-it-GGUF/resolve/main/Ko-Luxia-8B-it.f16.gguf) | f16 | 16.5 | 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. + +