commit 838457c8c13ee3c9732bd137708e33e747c3848c Author: ModelHub XC Date: Sat May 23 12:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d284ba5 --- /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 +llama3.1_korean_v1.3_sft_by_aidx.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.3_sft_by_aidx.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..60540e3 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: SEOKDONG/llama3.1_korean_v1.3_sft_by_aidx +datasets: +- AIDX-ktds/ko_leaderboard +language: +- ko +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ko +- leaderboard +- korean +- llama3.1 +- korean_8b +--- +## About + + + + + + +static quants of https://huggingface.co/SEOKDONG/llama3.1_korean_v1.3_sft_by_aidx + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.1_korean_v1.3_sft_by_aidx-GGUF).*** + +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/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.3_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.3_sft_by_aidx.f16.gguf) | f16 | 16.2 | 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/llama3.1_korean_v1.3_sft_by_aidx.IQ4_XS.gguf b/llama3.1_korean_v1.3_sft_by_aidx.IQ4_XS.gguf new file mode 100644 index 0000000..32b977f --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd8c7b4fd2bf3dba50cb5655b19d816bcf6470cc3c37781cfe2d91dd6d5e1b0 +size 4484364064 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q2_K.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q2_K.gguf new file mode 100644 index 0000000..fc54869 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6f9884bd52ebe88297d1364aebc1a776e4bdd63e0baef59c390477dd5889423 +size 3179132704 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_L.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_L.gguf new file mode 100644 index 0000000..c8054d0 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2dd8daa6335c4096c33dad24fea594ac77969d941719513c8e65e66abe1c5d +size 4321957664 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_M.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_M.gguf new file mode 100644 index 0000000..aa7b390 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c3ea8e3fbf8e441c526b27749339e0639275e81ab0ac1c98f9a93c899e6fb3 +size 4018919200 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_S.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_S.gguf new file mode 100644 index 0000000..0c5c9d7 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4846aebae2450984b86c7f7bc95cb6b92dac3ba389e57c072d756930e9c0fb0 +size 3664500512 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_M.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_M.gguf new file mode 100644 index 0000000..305b8fc --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3e6feb1a85788b3d44a7b84043f661b2170995d4fb90259100234c5d57547f3 +size 4920735520 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_S.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_S.gguf new file mode 100644 index 0000000..eaf9a42 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d6be4622ab8e1abe5604d755f89b5e8676c6e6433b73ae35eda6da26ab810c +size 4692670240 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_M.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_M.gguf new file mode 100644 index 0000000..6b391aa --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678e0a56b5fc0cb7d64beb75578c3823c479d3804c0bafb565b1ecd4bb054b06 +size 5732988704 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_S.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_S.gguf new file mode 100644 index 0000000..239c577 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6486f3c1f0fe550b3cfc9247f30bdcc22bf85a10ce23e7a4ec0ab14b068acf98 +size 5599295264 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q6_K.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q6_K.gguf new file mode 100644 index 0000000..f64c55e --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d6e2d43adc8df6a0a68e24f5e2e241598a772f0b8ed99970f7f838e2dda737 +size 6596007712 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.Q8_0.gguf b/llama3.1_korean_v1.3_sft_by_aidx.Q8_0.gguf new file mode 100644 index 0000000..1c6d544 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb5ee718b87cf5a2fde2208a573a9f0f85cf849a637eacdfaf075bde58a18a62 +size 8540772128 diff --git a/llama3.1_korean_v1.3_sft_by_aidx.f16.gguf b/llama3.1_korean_v1.3_sft_by_aidx.f16.gguf new file mode 100644 index 0000000..e3469d6 --- /dev/null +++ b/llama3.1_korean_v1.3_sft_by_aidx.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cc297f18649ffdf2fb11ac2d71c16d3524b616987cffb44b978a48371a1f440 +size 16068892448