commit a400b13a4569ee0c20696e14d1c55a262de43c76 Author: ModelHub XC Date: Mon Sep 28 16:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SKY-Ko-Llama3-8B-lora-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c9e92d --- /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 +SKY-Ko-Llama3-8B-lora.f16.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SKY-Ko-Llama3-8B-lora.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..73f47d1 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: SkyOrbis/SKY-Ko-Llama3-8B-lora +language: +- ko +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/SkyOrbis/SKY-Ko-Llama3-8B-lora + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-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/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SKY-Ko-Llama3-8B-lora-GGUF/resolve/main/SKY-Ko-Llama3-8B-lora.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/SKY-Ko-Llama3-8B-lora.IQ4_XS.gguf b/SKY-Ko-Llama3-8B-lora.IQ4_XS.gguf new file mode 100644 index 0000000..705fe94 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ebbdadbb79cf3a7593ff4904d68acb53c71d00d1bd70e90fd7e27aaa513480 +size 4484363264 diff --git a/SKY-Ko-Llama3-8B-lora.Q2_K.gguf b/SKY-Ko-Llama3-8B-lora.Q2_K.gguf new file mode 100644 index 0000000..ca36069 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26215b05c8947f3fd3bbdb1838b3a3fcaa4ca9be2633f22c914258042f74e9ea +size 3179131904 diff --git a/SKY-Ko-Llama3-8B-lora.Q3_K_L.gguf b/SKY-Ko-Llama3-8B-lora.Q3_K_L.gguf new file mode 100644 index 0000000..32a0096 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ab915eb976ff6644a8ada86f124edfe3130b2b3338572e8e3d706f95f0d3d3 +size 4321956864 diff --git a/SKY-Ko-Llama3-8B-lora.Q3_K_M.gguf b/SKY-Ko-Llama3-8B-lora.Q3_K_M.gguf new file mode 100644 index 0000000..488a1f7 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ebb82792b875e222f51690fe668f5327d53ae3d9485c9b70f3051df16478554 +size 4018918400 diff --git a/SKY-Ko-Llama3-8B-lora.Q3_K_S.gguf b/SKY-Ko-Llama3-8B-lora.Q3_K_S.gguf new file mode 100644 index 0000000..625d71c --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c431962452fc4a2416d2d156a52edf8bde259ca7653be2587af02c39462b9c16 +size 3664499712 diff --git a/SKY-Ko-Llama3-8B-lora.Q4_K_M.gguf b/SKY-Ko-Llama3-8B-lora.Q4_K_M.gguf new file mode 100644 index 0000000..52dccab --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a453c7b2904de372a075934b06bbffea3284ca692114f89945d8fd6595e376b +size 4920734720 diff --git a/SKY-Ko-Llama3-8B-lora.Q4_K_S.gguf b/SKY-Ko-Llama3-8B-lora.Q4_K_S.gguf new file mode 100644 index 0000000..7985599 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d298eddf41e99920f8c1c63376f7b1cf8cf1da49a73cc569d2de7dc163e408c3 +size 4692669440 diff --git a/SKY-Ko-Llama3-8B-lora.Q5_K_M.gguf b/SKY-Ko-Llama3-8B-lora.Q5_K_M.gguf new file mode 100644 index 0000000..c41ee0c --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c061f55cb0ebe44bf0382117e540506115295796a51afbce8d3e7708a651b250 +size 5732987904 diff --git a/SKY-Ko-Llama3-8B-lora.Q5_K_S.gguf b/SKY-Ko-Llama3-8B-lora.Q5_K_S.gguf new file mode 100644 index 0000000..3de8d27 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6943634467f682be541adee585511aa24d073576c05ae0c09973fe61d1b75ce1 +size 5599294464 diff --git a/SKY-Ko-Llama3-8B-lora.Q6_K.gguf b/SKY-Ko-Llama3-8B-lora.Q6_K.gguf new file mode 100644 index 0000000..b1e8e4b --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bbd9eff0d4731250fa42ddf7e940317173a7ff0d4a258f2de7e348c025fa200 +size 6596006912 diff --git a/SKY-Ko-Llama3-8B-lora.Q8_0.gguf b/SKY-Ko-Llama3-8B-lora.Q8_0.gguf new file mode 100644 index 0000000..bdbf182 --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43add40ff4ab2c7b4791f011259659f03d14ba4dca63dae04f71b162a3a2ce52 +size 8540771328 diff --git a/SKY-Ko-Llama3-8B-lora.f16.gguf b/SKY-Ko-Llama3-8B-lora.f16.gguf new file mode 100644 index 0000000..6a3348a --- /dev/null +++ b/SKY-Ko-Llama3-8B-lora.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a91d311eb247d96c1fbb5500270a4c97ba6aa1abaef396532bd236a1300beaf +size 16068891648