commit d706119bb465669a527631efd55ee0801692f2c2 Author: ModelHub XC Date: Thu Jul 23 15:22:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Ko-8B-ties-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..71c889a --- /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 +Llama-3-Ko-8B-ties.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Ko-8B-ties.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Ko-8B-ties.IQ4_XS.gguf b/Llama-3-Ko-8B-ties.IQ4_XS.gguf new file mode 100644 index 0000000..251a3eb --- /dev/null +++ b/Llama-3-Ko-8B-ties.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8796353b79068121b975b9ff30d0e02039dad274ff08ddbcc12cf2e46d4d829b +size 4484364096 diff --git a/Llama-3-Ko-8B-ties.Q2_K.gguf b/Llama-3-Ko-8B-ties.Q2_K.gguf new file mode 100644 index 0000000..77a2138 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97d2e8774562b58246e2a3969cb117d3d8f484e345044ebdfcf2dec6a24738b +size 3179132736 diff --git a/Llama-3-Ko-8B-ties.Q3_K_L.gguf b/Llama-3-Ko-8B-ties.Q3_K_L.gguf new file mode 100644 index 0000000..ccf9caa --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a98a20194f562bfa1708bbf6274130e0e6e7f1e9a53ca55f64082adf0f4b53 +size 4321957696 diff --git a/Llama-3-Ko-8B-ties.Q3_K_M.gguf b/Llama-3-Ko-8B-ties.Q3_K_M.gguf new file mode 100644 index 0000000..0e63eda --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:328c2f2071f5555789a9eaf66513ee15f0e5697533711c810be86f05b6f2b97c +size 4018919232 diff --git a/Llama-3-Ko-8B-ties.Q3_K_S.gguf b/Llama-3-Ko-8B-ties.Q3_K_S.gguf new file mode 100644 index 0000000..2be1730 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e90cdcbad3b2f31f7488e8d77885afdb0d99160a699174adc8926cffb07dfa +size 3664500544 diff --git a/Llama-3-Ko-8B-ties.Q4_K_M.gguf b/Llama-3-Ko-8B-ties.Q4_K_M.gguf new file mode 100644 index 0000000..f22c178 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e12ce00387bc4c58a6e5a923aedacdb279759090fe04d328d489d4148aaf3f8 +size 4920735552 diff --git a/Llama-3-Ko-8B-ties.Q4_K_S.gguf b/Llama-3-Ko-8B-ties.Q4_K_S.gguf new file mode 100644 index 0000000..fd9c896 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1205e2a8255ddb060c28c648981c8fa7811b165b236e40aee1873d77beb5d94f +size 4692670272 diff --git a/Llama-3-Ko-8B-ties.Q5_K_M.gguf b/Llama-3-Ko-8B-ties.Q5_K_M.gguf new file mode 100644 index 0000000..190c27f --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8d28231863356a9655764833a25097acbbe23230c423978cae09df98ecbc92e +size 5732988736 diff --git a/Llama-3-Ko-8B-ties.Q5_K_S.gguf b/Llama-3-Ko-8B-ties.Q5_K_S.gguf new file mode 100644 index 0000000..0213549 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342f2d960fa0d008cae6965120cd0aaa5e2216dc4dce70aa588a1df76363c794 +size 5599295296 diff --git a/Llama-3-Ko-8B-ties.Q6_K.gguf b/Llama-3-Ko-8B-ties.Q6_K.gguf new file mode 100644 index 0000000..1d57f34 --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513e98a9ffd9cc837dbace73c3fc3592d529c647f9388a9c51b460929eb2215f +size 6596007744 diff --git a/Llama-3-Ko-8B-ties.Q8_0.gguf b/Llama-3-Ko-8B-ties.Q8_0.gguf new file mode 100644 index 0000000..95ebdcc --- /dev/null +++ b/Llama-3-Ko-8B-ties.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa4e4d63d6011bd3a8bbb608f86e87574bc94c70ff8572e423db9bff142bb08 +size 8540772160 diff --git a/Llama-3-Ko-8B-ties.f16.gguf b/Llama-3-Ko-8B-ties.f16.gguf new file mode 100644 index 0000000..77112c7 --- /dev/null +++ b/Llama-3-Ko-8B-ties.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e7d74088c5a3abc16c562c514ee3f4c92e29fcfe6e4c2224436582e913d5509 +size 16068892480 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e94d7b8 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: kuotient/Llama-3-Ko-8B-ties +language: +- ko +library_name: transformers +license: other +license_name: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/kuotient/Llama-3-Ko-8B-ties + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-Ko-8B-ties-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/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Ko-8B-ties-GGUF/resolve/main/Llama-3-Ko-8B-ties.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. + +