commit e8b9f310ec9ce499a950deda33f9afdfd6b56d71 Author: ModelHub XC Date: Sat Jun 27 08:08:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/KoLlama-3-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..dca7f35 --- /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 +KoLlama-3-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +KoLlama-3-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/KoLlama-3-8B-Instruct.IQ3_M.gguf b/KoLlama-3-8B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..9a3b42a --- /dev/null +++ b/KoLlama-3-8B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeff9062f68b06babebead43803f62fd1aadc1f15887b8b8c13f5ac39ef67b73 +size 3785336480 diff --git a/KoLlama-3-8B-Instruct.IQ3_S.gguf b/KoLlama-3-8B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..c74ab9d --- /dev/null +++ b/KoLlama-3-8B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48fd878e2858b15892f8af6e63365bf7013d9f37b144a65fe91af70aa2ba22b2 +size 3682838176 diff --git a/KoLlama-3-8B-Instruct.IQ3_XS.gguf b/KoLlama-3-8B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..3c13cb1 --- /dev/null +++ b/KoLlama-3-8B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e212948f01232ad23480351b0917fb5373c5d5d2b5d18006a2d387de766ef1 +size 3519260320 diff --git a/KoLlama-3-8B-Instruct.IQ4_XS.gguf b/KoLlama-3-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..24590bb --- /dev/null +++ b/KoLlama-3-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85260e41ec5c413c3c8671a057c56fa114e4cf971631742c9e6c49266c4ca8a +size 4484875936 diff --git a/KoLlama-3-8B-Instruct.Q2_K.gguf b/KoLlama-3-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..c3394b7 --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab3a2d5e9c5f0f5f09fca0a28b973ee468c1db6141544d1af6fc113d341f4fc +size 3179644576 diff --git a/KoLlama-3-8B-Instruct.Q3_K_L.gguf b/KoLlama-3-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..87d584a --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b6699a6fce6e5fbd8de3c391b5463c7bbc1f314916802eda8eb06e821870398 +size 4322469536 diff --git a/KoLlama-3-8B-Instruct.Q3_K_M.gguf b/KoLlama-3-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..0eb7a84 --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d43d7aa8ade0f52d398f52c19f26a5926feedc719b38aebab7e576bcd1c7cb64 +size 4019431072 diff --git a/KoLlama-3-8B-Instruct.Q3_K_S.gguf b/KoLlama-3-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..6d291d2 --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42e81efe10b2291c12837ed4cba3c9edff21ee573b46dd08ea47d0541b57ce79 +size 3665012384 diff --git a/KoLlama-3-8B-Instruct.Q4_K_M.gguf b/KoLlama-3-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..4fe282f --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:930991660b3ee18ddb59a53fced7f9032ef90a63063a494b3e53615133f0209b +size 4921247392 diff --git a/KoLlama-3-8B-Instruct.Q4_K_S.gguf b/KoLlama-3-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..eeb0651 --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f226b8981d8a32e7347a4059a88b360e9b6169a59c3f0e52d1a5e3001a173116 +size 4693182112 diff --git a/KoLlama-3-8B-Instruct.Q5_K_M.gguf b/KoLlama-3-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..87902dd --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70f9a9f64c868d9b888a2efd535232a3c2dc1baacc3334a3de0807d4bf8aa18 +size 5733500576 diff --git a/KoLlama-3-8B-Instruct.Q5_K_S.gguf b/KoLlama-3-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..8a42a98 --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5269a832e1e492659ca516e65081de412d1c92d7a9aaa124bc231e50c28957 +size 5599807136 diff --git a/KoLlama-3-8B-Instruct.Q6_K.gguf b/KoLlama-3-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..cbf2a9f --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d68a6f07bbe4b27c9deeedcccfed87c8e34a047a949f1225a296be6c41e7965e +size 6596519584 diff --git a/KoLlama-3-8B-Instruct.Q8_0.gguf b/KoLlama-3-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..f22a97a --- /dev/null +++ b/KoLlama-3-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4651d8665f363deb2b2c15b67eb70b2f4c8168d103afad5d38d15be86980f30f +size 8541284000 diff --git a/KoLlama-3-8B-Instruct.f16.gguf b/KoLlama-3-8B-Instruct.f16.gguf new file mode 100644 index 0000000..7978333 --- /dev/null +++ b/KoLlama-3-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4eed9174a00a5b46ba64ebf37472982a701616ebd705573dfa82dcd48e5457 +size 16069404320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..945929a --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: fiveflow/KoLlama-3-8B-Instruct +language: +- ko +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- generated_from_trainer +--- +## About + + + + + +static quants of https://huggingface.co/fiveflow/KoLlama-3-8B-Instruct + + +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/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-GGUF/resolve/main/KoLlama-3-8B-Instruct.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. + +