commit 3ed7bf78ca1355cbb84b60edf5298117766eee3c Author: ModelHub XC Date: Wed Oct 21 15:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Granite-3.1-8B-instruct-Korean-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1f447e2 --- /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 +Granite-3.1-8B-instruct-Korean.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.f16.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Granite-3.1-8B-instruct-Korean.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Granite-3.1-8B-instruct-Korean.IQ4_XS.gguf b/Granite-3.1-8B-instruct-Korean.IQ4_XS.gguf new file mode 100644 index 0000000..7cb08a4 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b65c6c47c91b1da39ce975e0b0140d5549a01c317645952535caad7d3e8f8371 +size 4575992320 diff --git a/Granite-3.1-8B-instruct-Korean.Q2_K.gguf b/Granite-3.1-8B-instruct-Korean.Q2_K.gguf new file mode 100644 index 0000000..00337a0 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66b25ba8cae7198a828c57fa774fb2a589896419191ad0b5345d4aba5d3ab797 +size 3169652800 diff --git a/Granite-3.1-8B-instruct-Korean.Q3_K_L.gguf b/Granite-3.1-8B-instruct-Korean.Q3_K_L.gguf new file mode 100644 index 0000000..68caef4 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468589a37ecc2f543a8e433eee5b76283148d70ebacd5c1a4ee5f375f8af22f7 +size 4435940640 diff --git a/Granite-3.1-8B-instruct-Korean.Q3_K_M.gguf b/Granite-3.1-8B-instruct-Korean.Q3_K_M.gguf new file mode 100644 index 0000000..8335da0 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ef1d007a19cc1e207df1f58df9ab2083fa2a6d909769e628bf399a4272a741 +size 4083094816 diff --git a/Granite-3.1-8B-instruct-Korean.Q3_K_S.gguf b/Granite-3.1-8B-instruct-Korean.Q3_K_S.gguf new file mode 100644 index 0000000..4a33e44 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b01136b9289f383fbe55b430c12d85fff960acc92b7a03015f060306ac2b305 +size 3678999840 diff --git a/Granite-3.1-8B-instruct-Korean.Q4_K_M.gguf b/Granite-3.1-8B-instruct-Korean.Q4_K_M.gguf new file mode 100644 index 0000000..f6dc844 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e297b8776520059fa4d8e7875f949bc6fb8193bf313360258ad98ef4f08fe0 +size 5056109440 diff --git a/Granite-3.1-8B-instruct-Korean.Q4_K_S.gguf b/Granite-3.1-8B-instruct-Korean.Q4_K_S.gguf new file mode 100644 index 0000000..f96ee2f --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3470d271bb189038bd713100978877e6d1c1a55b0bf11665165011a19ee1d8 +size 4799011712 diff --git a/Granite-3.1-8B-instruct-Korean.Q5_K_M.gguf b/Granite-3.1-8B-instruct-Korean.Q5_K_M.gguf new file mode 100644 index 0000000..79469be --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0ff85bcf9f5d145207bcc39440c2b4eb4c7e66c5d9e0f44b4d9d2d599b1889 +size 5935866240 diff --git a/Granite-3.1-8B-instruct-Korean.Q5_K_S.gguf b/Granite-3.1-8B-instruct-Korean.Q5_K_S.gguf new file mode 100644 index 0000000..cf09150 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9693c341d05c84b3ee5a5f4643d8049d156ec834d36a0dd59584695aea04356 +size 5785461120 diff --git a/Granite-3.1-8B-instruct-Korean.Q6_K.gguf b/Granite-3.1-8B-instruct-Korean.Q6_K.gguf new file mode 100644 index 0000000..2cd9d06 --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11e3a46042b2c210bc3f22a489824268d8e6977f40d80e40f843c9223687508 +size 6870607840 diff --git a/Granite-3.1-8B-instruct-Korean.Q8_0.gguf b/Granite-3.1-8B-instruct-Korean.Q8_0.gguf new file mode 100644 index 0000000..7a175cb --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4063eea6b13fb8b1b075cc9bfa79219bf95a579d49b2dfb95c2dec4537a1a8ef +size 8898166560 diff --git a/Granite-3.1-8B-instruct-Korean.f16.gguf b/Granite-3.1-8B-instruct-Korean.f16.gguf new file mode 100644 index 0000000..052e26b --- /dev/null +++ b/Granite-3.1-8B-instruct-Korean.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d46de7c54300db89e27ae4dd2c041ab84327ad601c3e0206991b222e5fd6b3ba +size 16746780960 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3da9af7 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: mindw96/Granite-3.1-8B-instruct-Korean +datasets: +- beomi/KoAlpaca-v1.1a +language: +- ko +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/mindw96/Granite-3.1-8B-instruct-Korean + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-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/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q4_K_M.gguf) | Q4_K_M | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q5_K_S.gguf) | Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q6_K.gguf) | Q6_K | 7.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.Q8_0.gguf) | Q8_0 | 9.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Granite-3.1-8B-instruct-Korean-GGUF/resolve/main/Granite-3.1-8B-instruct-Korean.f16.gguf) | f16 | 16.8 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +