commit 0043e93caf4a5bfc3f00a3963c51b6613c077e35 Author: ModelHub XC Date: Mon Sep 14 12:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Ko-Llama3-Luxia-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a4e1d7 --- /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-Llama3-Luxia-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Ko-Llama3-Luxia-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Ko-Llama3-Luxia-8B.IQ4_XS.gguf b/Ko-Llama3-Luxia-8B.IQ4_XS.gguf new file mode 100644 index 0000000..6c00bdc --- /dev/null +++ b/Ko-Llama3-Luxia-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fc19b537400e3113da04fd1376bf65a0503ef155008a9344ed5fb5725fea20 +size 4582344480 diff --git a/Ko-Llama3-Luxia-8B.Q2_K.gguf b/Ko-Llama3-Luxia-8B.Q2_K.gguf new file mode 100644 index 0000000..90ae55a --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1538b19ba9a5804dc98845c15674aa4095aa9496c2f9d25afc153f73516d275 +size 3262523168 diff --git a/Ko-Llama3-Luxia-8B.Q3_K_L.gguf b/Ko-Llama3-Luxia-8B.Q3_K_L.gguf new file mode 100644 index 0000000..be88c32 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787e43071faf7d8b83e29fb6980dd00f98532d5fd3a36c7e0384a9793359630e +size 4412643104 diff --git a/Ko-Llama3-Luxia-8B.Q3_K_M.gguf b/Ko-Llama3-Luxia-8B.Q3_K_M.gguf new file mode 100644 index 0000000..bc70e56 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:033760c4cf93bd3e95e15b461a19d3b200292cd6c5d73bc81dd489f129421c0a +size 4109604640 diff --git a/Ko-Llama3-Luxia-8B.Q3_K_S.gguf b/Ko-Llama3-Luxia-8B.Q3_K_S.gguf new file mode 100644 index 0000000..7cd4379 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be28f8cba1a81cd2c5e0b8b8e02763ea1b2c314b6125999e3e7cad69496cca2b +size 3755185952 diff --git a/Ko-Llama3-Luxia-8B.Q4_K_M.gguf b/Ko-Llama3-Luxia-8B.Q4_K_M.gguf new file mode 100644 index 0000000..314366b --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e645aed3e427df90932fc93976f8237fe8a24bd163d661e4b80e2ed43eb95591 +size 5020960544 diff --git a/Ko-Llama3-Luxia-8B.Q4_K_S.gguf b/Ko-Llama3-Luxia-8B.Q4_K_S.gguf new file mode 100644 index 0000000..65b9b9a --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31bc5317e330461337e0695dc7f8dd53d798a2ba3bbf1e21932acc755f9cd115 +size 4792895264 diff --git a/Ko-Llama3-Luxia-8B.Q5_K_M.gguf b/Ko-Llama3-Luxia-8B.Q5_K_M.gguf new file mode 100644 index 0000000..a6c18b9 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f322b3b9780ddefb844275e0b338fc5f20eeff6d3adfa416561c550ba57a9d +size 5842192160 diff --git a/Ko-Llama3-Luxia-8B.Q5_K_S.gguf b/Ko-Llama3-Luxia-8B.Q5_K_S.gguf new file mode 100644 index 0000000..b2163e9 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6adb60acbab868ddb1d116d572012c8225fa8a35d2fa697126e738c3fab95a60 +size 5708498720 diff --git a/Ko-Llama3-Luxia-8B.Q6_K.gguf b/Ko-Llama3-Luxia-8B.Q6_K.gguf new file mode 100644 index 0000000..4c43dcd --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ae4b2f32b840f8788a5e6c254271c0064a5ca512f191709e39b981e9b2fb86 +size 6714750752 diff --git a/Ko-Llama3-Luxia-8B.Q8_0.gguf b/Ko-Llama3-Luxia-8B.Q8_0.gguf new file mode 100644 index 0000000..354bed7 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18aee84f039eb8db20ac5886cee5a360b21e44c2264a3bdbdf65c19fafdf7835 +size 8694306592 diff --git a/Ko-Llama3-Luxia-8B.f16.gguf b/Ko-Llama3-Luxia-8B.f16.gguf new file mode 100644 index 0000000..1bccb11 --- /dev/null +++ b/Ko-Llama3-Luxia-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:236a1afa4d8555a78aa9d554204ec4305b79e612caa160e9e2655d4da2e5920c +size 16357103392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bbce339 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: saltlux/Ko-Llama3-Luxia-8B +language: +- en +- ko +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- saltlux +- luxia +- meta +- llama-3 +- pytorch +--- +## About + + + + + + +static quants of https://huggingface.co/saltlux/Ko-Llama3-Luxia-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-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-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q5_K_M.gguf) | Q5_K_M | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Ko-Llama3-Luxia-8B-GGUF/resolve/main/Ko-Llama3-Luxia-8B.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. + +