commit 0ea5dd97a8e33994372f2822541e1c73cf67dcda Author: ModelHub XC Date: Thu Jun 18 10:10:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5eb29ca --- /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_v1.4_sft_by_aidx.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_sft_by_aidx.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1_korean_v1.4_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..407e251 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: SEOKDONG/llama3.1_korean_v1.4_sft_by_aidx +datasets: +- AIDX-ktds/ko_leaderboard +language: +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- ko_leaderboard +- upstage/open-ko-llm-leaderboard +- open-ko-llm-leaderboard +--- +## About + + + + + + +static quants of https://huggingface.co/SEOKDONG/llama3.1_korean_v1.4_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_v1.4_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_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_sft_by_aidx.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1_korean_v1.4_sft_by_aidx-GGUF/resolve/main/llama3.1_korean_v1.4_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_v1.4_sft_by_aidx.IQ4_XS.gguf b/llama3.1_korean_v1.4_sft_by_aidx.IQ4_XS.gguf new file mode 100644 index 0000000..c7e8f00 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2015c1c447f5c653dd46cc91a8e62155a51338d071425d5d45828a38468d90d2 +size 4484363808 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q2_K.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q2_K.gguf new file mode 100644 index 0000000..51c0fe3 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b28fac442aa589d6285914b59fb1767a7cad294082c84d75d0b2b437325687b +size 3179132448 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_L.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_L.gguf new file mode 100644 index 0000000..f4dec25 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65cf3c6c28167d936abd29bdd17d409a5f47855b55b323df050837a3a5847841 +size 4321957408 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_M.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_M.gguf new file mode 100644 index 0000000..504ec71 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561305bc7ffa3fd6516daabfc8ce9e7765d68efbca40781e865f5d5f6ce48c9f +size 4018918944 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_S.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_S.gguf new file mode 100644 index 0000000..10255e2 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d386d4e41bb801764f207e62d62d611aacdaeadfe7d70a3e8be204bcd8ff447b +size 3664500256 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_M.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_M.gguf new file mode 100644 index 0000000..afc27dd --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d17fea9394765b1addd4d35db01627f49126cbb03695f5ed95fd2449c366a0a0 +size 4920735264 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_S.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_S.gguf new file mode 100644 index 0000000..222d2a8 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4067a73345044f7f693524ca8502d6da6e36bed0a15b7b8513b46acbdcaddae7 +size 4692669984 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_M.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_M.gguf new file mode 100644 index 0000000..de47d6a --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a31f55cc39cd8f5658673299851eb7cc87865fe38b0e85fcc138c12c1a56d63 +size 5732988448 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_S.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_S.gguf new file mode 100644 index 0000000..3933593 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75325a4427e849bc5affb6e972508e719f2c1ba2b1ac9dbdb8c4f52c03d416a9 +size 5599295008 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q6_K.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q6_K.gguf new file mode 100644 index 0000000..d903df6 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c80c523763507b511738b4257cd62cfcfbf8953cf131d3080c806ac7a185444 +size 6596007456 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.Q8_0.gguf b/llama3.1_korean_v1.4_sft_by_aidx.Q8_0.gguf new file mode 100644 index 0000000..86e8b9f --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a11244580adf479a5ea9e5cd9850f74be4b66cb33808d3862303fa89a4db0ef7 +size 8540771872 diff --git a/llama3.1_korean_v1.4_sft_by_aidx.f16.gguf b/llama3.1_korean_v1.4_sft_by_aidx.f16.gguf new file mode 100644 index 0000000..5b6a9f5 --- /dev/null +++ b/llama3.1_korean_v1.4_sft_by_aidx.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:389594ef7bf4a878b813c60fb53437bcc04779c6325276e1ded00ea17c6f28bc +size 16068892192